diff --git a/.docker/llama-cpp-build-target.sh b/.docker/llama-cpp-build-target.sh
new file mode 100755
index 000000000000..177fdc7ad7cc
--- /dev/null
+++ b/.docker/llama-cpp-build-target.sh
@@ -0,0 +1,14 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+arch=${1:?target architecture is required}
+build_type=${2-}
+
+# GPU arm64 base images do not consistently provide the gcc-14 toolchain needed
+# to compile ggml's armv9.2 CPU variants. Keep their portable fallback until the
+# builder images can supply that compiler.
+if [ "$arch" = "arm64" ] && [ -n "$build_type" ]; then
+  echo llama-cpp-fallback
+else
+  echo llama-cpp-cpu-all
+fi
diff --git a/.docker/llama-cpp-compile.sh b/.docker/llama-cpp-compile.sh
index 112d43c160ed..32ff2a2392f0 100755
--- a/.docker/llama-cpp-compile.sh
+++ b/.docker/llama-cpp-compile.sh
@@ -18,10 +18,12 @@ if [[ -n "${CUDA_DOCKER_ARCH:-}" ]]; then
 fi
 
 cd /LocalAI/backend/cpp/llama-cpp
-if [ -z "${BUILD_TYPE:-}" ]; then
-  # Pure CPU image (BUILD_TYPE empty): one build with ggml CPU_ALL_VARIANTS replaces the
-  # per-microarch binaries (x86: avx/avx2/avx512/fallback; arm64: armv8.x/armv9.x). ggml
-  # dlopens the best libggml-cpu-*.so at runtime by probing host CPU features.
+BUILD_TARGET=$(/LocalAI/.docker/llama-cpp-build-target.sh "${TARGETARCH}" "${BUILD_TYPE:-}")
+if [ "$BUILD_TARGET" = "llama-cpp-cpu-all" ]; then
+  # One build with ggml CPU_ALL_VARIANTS replaces the per-microarch binaries (x86:
+  # avx/avx2/avx512/fallback; arm64: armv8.x/armv9.x). BUILD_TYPE remains in the
+  # environment, so GPU builds retain their accelerator backend while ggml dlopens the
+  # best CPU library when work is offloaded to the host.
   #
   # arm64: the CPU_ALL_VARIANTS table includes armv9.2 SME variants whose -march=...+sme is
   # rejected by the Ubuntu 24.04 default gcc-13. gcc-14 accepts it, so build the arm64
@@ -35,14 +37,8 @@ if [ -z "${BUILD_TYPE:-}" ]; then
     apt-get update -qq && apt-get install -y -qq gcc-14 g++-14
     export CC=gcc-14 CXX=g++-14
   fi
-  make llama-cpp-cpu-all
-else
-  # GPU build (cublas/hipblas/sycl/vulkan/...): the accelerator does the compute, so a
-  # single fallback CPU build is enough - no per-microarch CPU variants needed. (This also
-  # keeps the heavy GPU backend compile from also building the whole CPU variant matrix,
-  # and avoids the gcc-14 apt step on GPU base images such as nvidia l4t.)
-  make llama-cpp-fallback
 fi
+make "$BUILD_TARGET"
 make llama-cpp-grpc
 make llama-cpp-rpc-server
 
diff --git a/backend/cpp/bonsai/Makefile b/backend/cpp/bonsai/Makefile
index 9707372a9a11..673d7ab6d503 100644
--- a/backend/cpp/bonsai/Makefile
+++ b/backend/cpp/bonsai/Makefile
@@ -1,7 +1,7 @@
 
 # Pinned to the HEAD of the `prism` branch on https://github.com/PrismML-Eng/llama.cpp.
 # Auto-bumped nightly by .github/workflows/bump_deps.yaml.
-BONSAI_VERSION?=7529fdaaf99ffdc5ca71ace9c7409a56b27ad92f
+BONSAI_VERSION?=4dd165625bb6c020285eec8b342af25cf60233dd
 LLAMA_REPO?=https://github.com/PrismML-Eng/llama.cpp
 
 CMAKE_ARGS?=
diff --git a/backend/cpp/llama-cpp/run.sh b/backend/cpp/llama-cpp/run.sh
index 7610983194ea..3182801f18bd 100755
--- a/backend/cpp/llama-cpp/run.sh
+++ b/backend/cpp/llama-cpp/run.sh
@@ -12,10 +12,10 @@ grep -e "flags" /proc/cpuinfo | head -1
 
 BINARY=llama-cpp-fallback
 
-# CPU images (x86, arm64, darwin) ship a single llama-cpp-cpu-all built with ggml
+# CPU images and x86 GPU images ship a single llama-cpp-cpu-all built with ggml
 # CPU_ALL_VARIANTS: ggml's backend registry dlopens the best libggml-cpu-*.so for this
-# host, so no shell-side AVX probing. GPU images (cublas/sycl/vulkan/hipblas) ship only
-# llama-cpp-fallback (the accelerator does the compute), so fall back to it when absent.
+# host, so no shell-side AVX probing. GPU arm64 images still ship llama-cpp-fallback
+# until their builder toolchains support ggml's complete arm variant matrix.
 if [ -e "$CURDIR"/llama-cpp-cpu-all ]; then
 	BINARY=llama-cpp-cpu-all
 fi
@@ -76,4 +76,4 @@ echo "Using binary: $BINARY"
 exec "$CURDIR"/$BINARY "$@"
 
 # We should never reach this point, however just in case we do, run fallback
-exec "$CURDIR"/llama-cpp-fallback "$@"
\ No newline at end of file
+exec "$CURDIR"/llama-cpp-fallback "$@"
diff --git a/backend/cpp/turboquant/Makefile b/backend/cpp/turboquant/Makefile
index 5ec20b86af8c..162d09fd1268 100644
--- a/backend/cpp/turboquant/Makefile
+++ b/backend/cpp/turboquant/Makefile
@@ -1,7 +1,7 @@
 
 # Pinned to the HEAD of feature/turboquant-kv-cache on https://github.com/TheTom/llama-cpp-turboquant.
 # Auto-bumped nightly by .github/workflows/bump_deps.yaml.
-TURBOQUANT_VERSION?=c26cbdffcf6fc9b7430cd6b117757e9a3f70b7ea
+TURBOQUANT_VERSION?=8a891f4b566efdbd3cea92fafee3227a0a267683
 LLAMA_REPO?=https://github.com/TheTom/llama-cpp-turboquant
 
 CMAKE_ARGS?=
diff --git a/core/gallery/importers/mlx.go b/core/gallery/importers/mlx.go
index 2698fe72fe5f..1f23b48dc2ce 100644
--- a/core/gallery/importers/mlx.go
+++ b/core/gallery/importers/mlx.go
@@ -3,6 +3,7 @@ package importers
 import (
 	"encoding/json"
 	"path/filepath"
+	"slices"
 	"strings"
 
 	"github.com/mudler/LocalAI/core/config"
@@ -31,7 +32,7 @@ func (i *MLXImporter) Match(details Details) bool {
 	}
 
 	b, ok := preferencesMap["backend"].(string)
-	if ok && b == "mlx" || b == "mlx-vlm" {
+	if ok && slices.Contains([]string{"mlx", "mlx-vlm", "mlx-audio"}, b) {
 		return true
 	}
 
@@ -71,19 +72,32 @@ func (i *MLXImporter) Import(details Details) (gallery.ModelConfig, error) {
 	// (issue #10269). Send them to the mlx-vlm backend, which applies the
 	// processor-aware chat template.
 	backend := "mlx"
-	if details.HuggingFace != nil && details.HuggingFace.PipelineTag == "image-text-to-text" {
-		backend = "mlx-vlm"
+	usecases := []string{config.UsecaseChat}
+	useTokenizerTemplate := true
+	if details.HuggingFace != nil {
+		switch details.HuggingFace.PipelineTag {
+		case "image-text-to-text":
+			backend = "mlx-vlm"
+		case "text-to-speech":
+			backend = "mlx-audio"
+			usecases = []string{config.UsecaseTTS}
+			useTokenizerTemplate = false
+		}
 	}
 	// An explicit backend preference always wins.
 	b, ok := preferencesMap["backend"].(string)
 	if ok {
 		backend = b
+		if backend == "mlx-audio" {
+			usecases = []string{config.UsecaseTTS}
+			useTokenizerTemplate = false
+		}
 	}
 
 	modelConfig := config.ModelConfig{
 		Name:                name,
 		Description:         description,
-		KnownUsecaseStrings: []string{config.UsecaseChat},
+		KnownUsecaseStrings: usecases,
 		Backend:             backend,
 		PredictionOptions: schema.PredictionOptions{
 			BasicModelRequest: schema.BasicModelRequest{
@@ -91,7 +105,7 @@ func (i *MLXImporter) Import(details Details) (gallery.ModelConfig, error) {
 			},
 		},
 		TemplateConfig: config.TemplateConfig{
-			UseTokenizerTemplate: true,
+			UseTokenizerTemplate: useTokenizerTemplate,
 		},
 	}
 
diff --git a/core/gallery/importers/mlx_test.go b/core/gallery/importers/mlx_test.go
index 2eeaef3fbc9e..9c346455766c 100644
--- a/core/gallery/importers/mlx_test.go
+++ b/core/gallery/importers/mlx_test.go
@@ -48,6 +48,16 @@ var _ = Describe("MLXImporter", func() {
 			Expect(result).To(BeTrue())
 		})
 
+		It("should match when backend preference is mlx-audio", func() {
+			preferences := json.RawMessage(`{"backend": "mlx-audio"}`)
+			details := importers.Details{
+				URI:         "https://example.com/model",
+				Preferences: preferences,
+			}
+
+			Expect(importer.Match(details)).To(BeTrue())
+		})
+
 		It("should not match when URI does not contain mlx-community/ and no backend preference", func() {
 			details := importers.Details{
 				URI: "https://huggingface.co/other-org/test-model",
@@ -123,6 +133,21 @@ var _ = Describe("MLXImporter", func() {
 			Expect(modelConfig.ConfigFile).To(ContainSubstring("backend: mlx-vlm"))
 		})
 
+		It("should configure explicit mlx-audio imports for text-to-speech", func() {
+			preferences := json.RawMessage(`{"backend": "mlx-audio"}`)
+			details := importers.Details{
+				URI:         "https://huggingface.co/mlx-community/Kokoro-82M-4bit",
+				Preferences: preferences,
+			}
+
+			modelConfig, err := importer.Import(details)
+
+			Expect(err).ToNot(HaveOccurred())
+			Expect(modelConfig.ConfigFile).To(ContainSubstring("backend: mlx-audio"))
+			Expect(modelConfig.ConfigFile).To(ContainSubstring("- tts"))
+			Expect(modelConfig.ConfigFile).ToNot(ContainSubstring("use_tokenizer_template: true"))
+		})
+
 		It("should auto-route vision-language models to the mlx-vlm backend", func() {
 			// gemma-4 E4B and similar VLMs declare pipeline_tag
 			// "image-text-to-text" on HuggingFace. The text-only mlx-lm
@@ -143,6 +168,23 @@ var _ = Describe("MLXImporter", func() {
 			Expect(modelConfig.ConfigFile).To(ContainSubstring("backend: mlx-vlm"))
 		})
 
+		It("should auto-route text-to-speech models to the mlx-audio backend", func() {
+			details := importers.Details{
+				URI: "https://huggingface.co/mlx-community/Kokoro-82M-4bit",
+				HuggingFace: &hfapi.ModelDetails{
+					ModelID:     "mlx-community/Kokoro-82M-4bit",
+					PipelineTag: "text-to-speech",
+				},
+			}
+
+			modelConfig, err := importer.Import(details)
+
+			Expect(err).ToNot(HaveOccurred())
+			Expect(modelConfig.ConfigFile).To(ContainSubstring("backend: mlx-audio"))
+			Expect(modelConfig.ConfigFile).To(ContainSubstring("- tts"))
+			Expect(modelConfig.ConfigFile).ToNot(ContainSubstring("use_tokenizer_template: true"))
+		})
+
 		It("should keep text-only models on the plain mlx backend", func() {
 			details := importers.Details{
 				URI: "https://huggingface.co/mlx-community/Llama-3.2-1B-Instruct-4bit",
diff --git a/core/http/endpoints/localai/backend.go b/core/http/endpoints/localai/backend.go
index 3d4a25b3313a..221e2829a199 100644
--- a/core/http/endpoints/localai/backend.go
+++ b/core/http/endpoints/localai/backend.go
@@ -38,6 +38,7 @@ var knownPrefOnlyBackends = []schema.KnownBackend{
 	{Name: "whisperx", Modality: "asr", AutoDetect: false, Description: "WhisperX transcription (preference-only)"},
 	{Name: "crispasr", Modality: "asr", AutoDetect: false, Description: "CrispASR multi-architecture transcription (preference-only)"},
 	// TTS
+	{Name: "mlx-audio", Modality: "tts", AutoDetect: false, Description: "MLX-Audio text-to-speech models (auto-detected; pref-only fallback)"},
 	{Name: "kokoros", Modality: "tts", AutoDetect: false, Description: "Kokoros TTS (preference-only)"},
 	{Name: "qwen-tts", Modality: "tts", AutoDetect: false, Description: "Qwen TTS (preference-only)"},
 	{Name: "qwen3-tts-cpp", Modality: "tts", AutoDetect: false, Description: "Qwen3 TTS C++ (preference-only)"},
diff --git a/core/http/endpoints/localai/backend_test.go b/core/http/endpoints/localai/backend_test.go
index 3c43fb60c870..04a486354619 100644
--- a/core/http/endpoints/localai/backend_test.go
+++ b/core/http/endpoints/localai/backend_test.go
@@ -152,6 +152,7 @@ var _ = Describe("Backend Endpoints", func() {
 			expectPrefOnly("tinygrad", "text")
 			expectPrefOnly("trl", "text")
 			expectPrefOnly("mlx-vlm", "text")
+			expectPrefOnly("mlx-audio", "tts")
 			expectPrefOnly("whisperx", "asr")
 			expectPrefOnly("crispasr", "asr")
 			expectPrefOnly("kokoros", "tts")
diff --git a/docs/content/getting-started/models.md b/docs/content/getting-started/models.md
index d3345a346541..1bd612358e85 100644
--- a/docs/content/getting-started/models.md
+++ b/docs/content/getting-started/models.md
@@ -80,6 +80,12 @@ The WebUI provides a powerful model import interface that supports both simple a
    - Custom preferences
 5. Click "Import Model" to start the import process
 
+Repositories under `mlx-community` are imported with the native MLX backend.
+LocalAI uses Hugging Face's pipeline metadata to select `mlx-vlm` for
+vision-language models and `mlx-audio` for text-to-speech models; other MLX
+repositories use `mlx`. An explicit backend selection in the import form always
+overrides this automatic routing.
+
 ### Advanced Import Mode
 
 For full control over model configuration:
diff --git a/gallery/index.yaml b/gallery/index.yaml
index 617dc2466bb7..05ea2ddec38b 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -1,4 +1,48 @@
 ---
+- name: "deepseek-v4-flash-0731"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/unsloth/DeepSeek-V4-Flash-0731-GGUF
+  description: |
+    # DeepSeek-V4-Flash-0731
+
+    Technical Report👁️
+
+    ## Introduction
+
+    **DeepSeek-V4-Flash-0731** is the official release of **DeepSeek-V4-Flash**, superseding the preview version, with substantially enhanced agentic capabilities. It has the same model structure as DeepSeek-V4-Flash-DSpark, i.e. it comes with a speculative decoding module attached.
+
+    DeepSeek-V4-Flash-0731 outperforms DeepSeek-V4-Pro (Preview) on benchmarks listed below despite its far smaller activated parameter count, and is broadly competitive with the strongest proprietary models available.
+
+    Notes:
+
+    1. For the Code Agent tasks among the public benchmarks above, DeepSeek-V4-Flash-0731 is evaluated with the minimal mode of DeepSeek Harness (to be released) as the agent framework, using the `max` reasoning effort level with `temperature = 1.0, top_p = 0.95`.
+    2. † DSBench-FullStack is an internal full-stack development test set; DSBench-Hard is an internal test set of difficult coding-agent problems.
+
+    ## Chat Template
+
+    ...
+  license: "mit"
+  tags:
+    - llm
+    - gguf
+    - deepseek
+  icon: https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg
+  overrides:
+    backend: ds4
+    function:
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    parameters:
+      model: ds4flash.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: ds4flash.gguf
+      sha256: ""
+      uri: https://huggingface.co/unsloth/DeepSeek-V4-Flash-0731-GGUF
 - name: "parable-granite-4.1-3b-claude-fable-5"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
@@ -897,6 +941,90 @@
     - filename: llama-cpp/mmproj/inkling-UD-Q4_K_XL/mmproj-BF16.gguf
       sha256: 662c925e1df293cfba16ffd6bd53dac31d3c73160ba65dff7270d7a70f351e91
       uri: https://huggingface.co/unsloth/inkling-GGUF/resolve/main/mmproj-BF16.gguf
+- &inkling-small
+  name: "inkling-small"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/thinkingmachines/Inkling-Small
+    - https://huggingface.co/unsloth/Inkling-Small-GGUF
+  description: |
+    Inkling Small is a 276B-parameter mixture-of-experts multimodal model with 12B active parameters for text, image, and audio understanding, instruction following, coding, and tool use. This entry uses the Q4_K_M GGUF quantization, whose five language-model shards total approximately 162.5 GB.
+  license: "apache-2.0"
+  tags:
+    - llm
+    - gguf
+    - vision
+    - audio
+    - multimodal
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    mmproj: llama-cpp/mmproj/Inkling-Small-UD-Q4_K_M/mmproj-BF16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/Inkling-Small-UD-Q4_K_M/Inkling-Small-UD-Q4_K_M-00001-of-00005.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/Inkling-Small-UD-Q4_K_M/Inkling-Small-UD-Q4_K_M-00001-of-00005.gguf
+      sha256: a51ac3f439198f2817219edd582be4b600c273be24e78cbd58ebff982d9f007e
+      uri: https://huggingface.co/unsloth/Inkling-Small-GGUF/resolve/main/UD-Q4_K_M/Inkling-Small-UD-Q4_K_M-00001-of-00005.gguf
+    - filename: llama-cpp/models/Inkling-Small-UD-Q4_K_M/Inkling-Small-UD-Q4_K_M-00002-of-00005.gguf
+      sha256: 3dccdd473cc3a191e6028f6105b01831ed3a8dc30ec4e02679f9e0c2ccb59671
+      uri: https://huggingface.co/unsloth/Inkling-Small-GGUF/resolve/main/UD-Q4_K_M/Inkling-Small-UD-Q4_K_M-00002-of-00005.gguf
+    - filename: llama-cpp/models/Inkling-Small-UD-Q4_K_M/Inkling-Small-UD-Q4_K_M-00003-of-00005.gguf
+      sha256: 1a7edf29bda1d278b4668e1a082d7db634b845a53ea58c918a8cea1f9006c21c
+      uri: https://huggingface.co/unsloth/Inkling-Small-GGUF/resolve/main/UD-Q4_K_M/Inkling-Small-UD-Q4_K_M-00003-of-00005.gguf
+    - filename: llama-cpp/models/Inkling-Small-UD-Q4_K_M/Inkling-Small-UD-Q4_K_M-00004-of-00005.gguf
+      sha256: 376f67568438da96b10566730e8a9e17e3f665ab1b9d82eba48ec33708b172f7
+      uri: https://huggingface.co/unsloth/Inkling-Small-GGUF/resolve/main/UD-Q4_K_M/Inkling-Small-UD-Q4_K_M-00004-of-00005.gguf
+    - filename: llama-cpp/models/Inkling-Small-UD-Q4_K_M/Inkling-Small-UD-Q4_K_M-00005-of-00005.gguf
+      sha256: e34364af0d04d2d295bc374f1a4fa80002e4277db1bcf4b56240dbd443ac21d3
+      uri: https://huggingface.co/unsloth/Inkling-Small-GGUF/resolve/main/UD-Q4_K_M/Inkling-Small-UD-Q4_K_M-00005-of-00005.gguf
+    - filename: llama-cpp/mmproj/Inkling-Small-UD-Q4_K_M/mmproj-BF16.gguf
+      sha256: 05d4475a956030be87b099865d6552a541a476db8cc3e266fcfa7c5a24846248
+      uri: https://huggingface.co/unsloth/Inkling-Small-GGUF/resolve/main/mmproj-BF16.gguf
+  variants:
+    - model: inkling-small-iq2-m
+- !!merge <<: *inkling-small
+  name: "inkling-small-iq2-m"
+  description: |
+    Inkling Small is a 276B-parameter mixture-of-experts multimodal model with 12B active parameters for text, image, and audio understanding, instruction following, coding, and tool use. This entry uses the IQ2_M GGUF quantization, whose three language-model shards total approximately 82.4 GB.
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    mmproj: llama-cpp/mmproj/Inkling-Small-UD-IQ2_M/mmproj-BF16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/Inkling-Small-UD-IQ2_M/Inkling-Small-UD-IQ2_M-00001-of-00003.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/Inkling-Small-UD-IQ2_M/Inkling-Small-UD-IQ2_M-00001-of-00003.gguf
+      sha256: 3b6ace30e488ad26e816cdba4e42714f40110a3142a210bd5c2e48f69e27cb31
+      uri: https://huggingface.co/unsloth/Inkling-Small-GGUF/resolve/main/UD-IQ2_M/Inkling-Small-UD-IQ2_M-00001-of-00003.gguf
+    - filename: llama-cpp/models/Inkling-Small-UD-IQ2_M/Inkling-Small-UD-IQ2_M-00002-of-00003.gguf
+      sha256: 5ca94e858ae116eb513a2af1facd35844d42ef4a209e1d85cc4ecc73cd21b894
+      uri: https://huggingface.co/unsloth/Inkling-Small-GGUF/resolve/main/UD-IQ2_M/Inkling-Small-UD-IQ2_M-00002-of-00003.gguf
+    - filename: llama-cpp/models/Inkling-Small-UD-IQ2_M/Inkling-Small-UD-IQ2_M-00003-of-00003.gguf
+      sha256: 8a84e00d4625d52491969f88f24f0999bc77527b7fa1d15cbe44ef88235bb377
+      uri: https://huggingface.co/unsloth/Inkling-Small-GGUF/resolve/main/UD-IQ2_M/Inkling-Small-UD-IQ2_M-00003-of-00003.gguf
+    - filename: llama-cpp/mmproj/Inkling-Small-UD-IQ2_M/mmproj-BF16.gguf
+      sha256: 05d4475a956030be87b099865d6552a541a476db8cc3e266fcfa7c5a24846248
+      uri: https://huggingface.co/unsloth/Inkling-Small-GGUF/resolve/main/mmproj-BF16.gguf
+  variants: []
 - name: "qwythos-9b-v2"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
@@ -5262,6 +5390,82 @@
     - filename: llama-cpp/models/Qwen3.5-35B-A3B-APEX-GGUF/Qwen3.5-35B-A3B-APEX-Quality.gguf
       sha256: 50887b60c77ee5c95bc3657814ae993abcab7b2d71868b9af1e84d6badd09a57
       uri: https://huggingface.co/mudler/Qwen3.5-35B-A3B-APEX-GGUF/resolve/main/Qwen3.5-35B-A3B-APEX-Quality.gguf
+- &fara1-5-9b
+  name: fara1.5-9b
+  url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  variants:
+    - model: fara1.5-9b-q8
+  urls:
+    - https://huggingface.co/microsoft/Fara1.5-9B
+    - https://huggingface.co/bartowski/Fara1.5-9B-GGUF
+  description: |
+    Fara1.5-9B is Microsoft's 9B-parameter multimodal computer-use agent for web browsers, fine-tuned from Qwen3.5-9B. It accepts screenshots and text, emits structured browser actions, supports a 262K-token context, and should be deployed with appropriate sandboxing and user-confirmation controls. This entry uses the recommended Q4_K_M GGUF quantization.
+  license: mit
+  tags:
+    - fara
+    - qwen
+    - qwen3.5
+    - 9b
+    - llm
+    - gguf
+    - quantized
+    - chat
+    - vision
+    - multimodal
+    - agent
+    - computer-use
+    - gpu
+    - cpu
+  last_checked: "2026-08-01"
+  overrides:
+    backend: llama-cpp
+    function:
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: llama-cpp/mmproj/Fara1.5-9B-GGUF/mmproj-Fara1.5-9B-f16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/Fara1.5-9B-GGUF/Fara1.5-9B-Q4_K_M.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/Fara1.5-9B-GGUF/Fara1.5-9B-Q4_K_M.gguf
+      sha256: a02e7220337b87290bca7ef7225ba4afa7104efa05c0851de6c29ec9c5d04c7d
+      uri: huggingface://bartowski/Fara1.5-9B-GGUF/Fara1.5-9B-Q4_K_M.gguf
+    - filename: llama-cpp/mmproj/Fara1.5-9B-GGUF/mmproj-Fara1.5-9B-f16.gguf
+      sha256: 97b423c81719ffc367124a9739d6feb6f62d62f60869a6d385a701b963ce1906
+      uri: huggingface://bartowski/Fara1.5-9B-GGUF/mmproj-Fara1.5-9B-f16.gguf
+- !!merge <<: *fara1-5-9b
+  name: fara1.5-9b-q8
+  variants: []
+  description: |
+    Fara1.5-9B is Microsoft's 9B-parameter multimodal computer-use agent for web browsers, fine-tuned from Qwen3.5-9B. It accepts screenshots and text, emits structured browser actions, supports a 262K-token context, and should be deployed with appropriate sandboxing and user-confirmation controls. This entry uses the higher-quality Q8_0 GGUF quantization.
+  overrides:
+    backend: llama-cpp
+    function:
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: llama-cpp/mmproj/Fara1.5-9B-GGUF/mmproj-Fara1.5-9B-f16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/Fara1.5-9B-GGUF/Fara1.5-9B-Q8_0.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/Fara1.5-9B-GGUF/Fara1.5-9B-Q8_0.gguf
+      sha256: a2e30cca7aec006266308153ae781347505af16baa514bbd4e0e3f4a79ea3a22
+      uri: huggingface://bartowski/Fara1.5-9B-GGUF/Fara1.5-9B-Q8_0.gguf
+    - filename: llama-cpp/mmproj/Fara1.5-9B-GGUF/mmproj-Fara1.5-9B-f16.gguf
+      sha256: 97b423c81719ffc367124a9739d6feb6f62d62f60869a6d385a701b963ce1906
+      uri: huggingface://bartowski/Fara1.5-9B-GGUF/mmproj-Fara1.5-9B-f16.gguf
 - name: fara1.5-27b
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   variants:
@@ -6010,14 +6214,14 @@
     - instruction-tuned
     - code
     - math
-  last_checked: "2026-07-28"
+  last_checked: "2026-08-01"
   overrides:
     parameters:
-      model: nanbeige4.2-3b-Q8_0.gguf
+      model: Nanbeige4.2-3B-Q8_0.gguf
   files:
-    - filename: nanbeige4.2-3b-Q8_0.gguf
-      sha256: 44707bb25e7ba3f2b0b5f3c2311da95ee3676986dd2014ce2aaeb14113590e33
-      uri: huggingface://owao/Nanbeige4.2-3B-GGUF/nanbeige4.2-3b-Q8_0.gguf
+    - filename: Nanbeige4.2-3B-Q8_0.gguf
+      sha256: 4f8bd17cdf58bea2a94aef03457e0b8f019c26fe4daee7ae49b61bfa935a9126
+      uri: huggingface://owao/Nanbeige4.2-3B-GGUF/Nanbeige4.2-3B-Q8_0.gguf
 - name: nanbeige4.2-3b
   url: github:mudler/LocalAI/gallery/nanbeige4.2.yaml@master
   urls:
@@ -6040,16 +6244,16 @@
     - instruction-tuned
     - code
     - math
-  last_checked: "2026-07-28"
+  last_checked: "2026-08-01"
   variants:
     - model: nanbeige4.2-3b-q8
   overrides:
     parameters:
-      model: nanbeige4.2-3b-Q4_K_M.gguf
+      model: Nanbeige4.2-3B-Q4_K_M.gguf
   files:
-    - filename: nanbeige4.2-3b-Q4_K_M.gguf
-      sha256: 9ffd17d14472ff208409b3f51a6d87a5e5ec1b878b9a6f4dfe15c2a883366104
-      uri: huggingface://owao/Nanbeige4.2-3B-GGUF/nanbeige4.2-3b-Q4_K_M.gguf
+    - filename: Nanbeige4.2-3B-Q4_K_M.gguf
+      sha256: ffe1b9b8ee95ec4b962c379905aa8be6f72ae9c4645c6c70e3b6ff7b197e6ef4
+      uri: huggingface://owao/Nanbeige4.2-3B-GGUF/Nanbeige4.2-3B-Q4_K_M.gguf
 - name: nemo-parakeet-tdt-0.6b
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
diff --git a/pkg/utils/untar.go b/pkg/utils/untar.go
index cb65bb6b5ec0..c8521648e240 100644
--- a/pkg/utils/untar.go
+++ b/pkg/utils/untar.go
@@ -70,6 +70,11 @@ func ExtractArchive(archive, dst string) error {
 		if f.FileInfo.Mode()&os.ModeSymlink != 0 {
 			return fmt.Errorf("archive contains a symlink")
 		}
+		if linkname, ok := archiveMemberLinkname(f); ok {
+			if err := validateArchiveMemberPath(extractRoot, linkname); err != nil {
+				return err
+			}
+		}
 		return nil
 	})
 
@@ -95,6 +100,18 @@ func archiveMemberName(f archiver.File) string {
 	}
 }
 
+// archiveMemberLinkname reports the target of a tar hardlink member, which carries a regular file mode and so is not caught by the symlink check.
+func archiveMemberLinkname(f archiver.File) (string, bool) {
+	switch h := f.Header.(type) {
+	case tar.Header:
+		return h.Linkname, h.Typeflag == tar.TypeLink
+	case *tar.Header:
+		return h.Linkname, h.Typeflag == tar.TypeLink
+	default:
+		return "", false
+	}
+}
+
 func validateArchiveMemberPath(root, name string) error {
 	if name == "" {
 		return fmt.Errorf("archive contains an empty path")
diff --git a/pkg/utils/untar_test.go b/pkg/utils/untar_test.go
index e82b3611f790..7d40125803b7 100644
--- a/pkg/utils/untar_test.go
+++ b/pkg/utils/untar_test.go
@@ -3,6 +3,7 @@ package utils_test
 import (
 	"archive/tar"
 	"archive/zip"
+	"compress/gzip"
 	"os"
 	"path/filepath"
 
@@ -59,6 +60,53 @@ var _ = Describe("utils/archive tests", func() {
 		Expect(err.Error()).To(ContainSubstring("unsafe path"))
 		Expect(filepath.Join(tmpDir, "escaped.txt")).ToNot(BeAnExistingFile())
 	})
+
+	It("rejects tar hardlinks that overwrite a file outside the destination", func() {
+		tmpDir := GinkgoT().TempDir()
+		archivePath := filepath.Join(tmpDir, "model.tar.gz")
+		extractPath := filepath.Join(tmpDir, "models")
+		outsidePath := filepath.Join(tmpDir, "outside.txt")
+
+		Expect(os.WriteFile(outsidePath, []byte("original"), 0o600)).To(Succeed())
+		Expect(writeTarGzArchiveWithHardlinkedFile(archivePath, "payload.bin", "../outside.txt", "overwritten")).To(Succeed())
+
+		err := ExtractArchive(archivePath, extractPath)
+
+		Expect(err).To(HaveOccurred())
+		Expect(err.Error()).To(ContainSubstring("unsafe path"))
+
+		contents, readErr := os.ReadFile(outsidePath)
+		Expect(readErr).ToNot(HaveOccurred())
+		Expect(string(contents)).To(Equal("original"))
+	})
+
+	It("extracts tar hardlinks that stay inside the destination", func() {
+		tmpDir := GinkgoT().TempDir()
+		archivePath := filepath.Join(tmpDir, "model.tar.gz")
+		extractPath := filepath.Join(tmpDir, "models")
+
+		Expect(writeTarGzArchiveWithInternalHardlink(archivePath, "model.bin", "alias.bin", "weights")).To(Succeed())
+
+		Expect(ExtractArchive(archivePath, extractPath)).To(Succeed())
+
+		extracted, err := os.ReadFile(filepath.Join(extractPath, "alias.bin"))
+		Expect(err).ToNot(HaveOccurred())
+		Expect(string(extracted)).To(Equal("weights"))
+	})
+
+	It("rejects tar hardlinks that point outside the destination", func() {
+		tmpDir := GinkgoT().TempDir()
+		archivePath := filepath.Join(tmpDir, "model.tar")
+		extractPath := filepath.Join(tmpDir, "models")
+
+		Expect(writeTarArchiveWithHardlink(archivePath, "payload.bin", "../escaped.txt")).To(Succeed())
+
+		err := ExtractArchive(archivePath, extractPath)
+
+		Expect(err).To(HaveOccurred())
+		Expect(err.Error()).To(ContainSubstring("unsafe path"))
+		Expect(filepath.Join(tmpDir, "escaped.txt")).ToNot(BeAnExistingFile())
+	})
 })
 
 func writeZipArchive(path string, files map[string]string) (err error) {
@@ -126,3 +174,121 @@ func writeTarArchive(path string, files map[string]string) (err error) {
 
 	return nil
 }
+
+func writeTarArchiveWithHardlink(path, name, linkname string) (err error) {
+	out, err := os.Create(path)
+	if err != nil {
+		return err
+	}
+	defer func() {
+		if closeErr := out.Close(); err == nil {
+			err = closeErr
+		}
+	}()
+
+	writer := tar.NewWriter(out)
+	defer func() {
+		if closeErr := writer.Close(); err == nil {
+			err = closeErr
+		}
+	}()
+
+	return writer.WriteHeader(&tar.Header{
+		Name:     name,
+		Linkname: linkname,
+		Typeflag: tar.TypeLink,
+		Mode:     0o600,
+	})
+}
+
+func writeTarGzArchiveWithHardlinkedFile(path, name, linkname, contents string) (err error) {
+	out, err := os.Create(path)
+	if err != nil {
+		return err
+	}
+	defer func() {
+		if closeErr := out.Close(); err == nil {
+			err = closeErr
+		}
+	}()
+
+	compressor := gzip.NewWriter(out)
+	defer func() {
+		if closeErr := compressor.Close(); err == nil {
+			err = closeErr
+		}
+	}()
+
+	writer := tar.NewWriter(compressor)
+	defer func() {
+		if closeErr := writer.Close(); err == nil {
+			err = closeErr
+		}
+	}()
+
+	if err := writer.WriteHeader(&tar.Header{
+		Name:     name,
+		Linkname: linkname,
+		Typeflag: tar.TypeLink,
+		Mode:     0o600,
+	}); err != nil {
+		return err
+	}
+
+	data := []byte(contents)
+	if err := writer.WriteHeader(&tar.Header{
+		Name: name,
+		Mode: 0o600,
+		Size: int64(len(data)),
+	}); err != nil {
+		return err
+	}
+	_, err = writer.Write(data)
+
+	return err
+}
+
+func writeTarGzArchiveWithInternalHardlink(path, targetName, linkName, contents string) (err error) {
+	out, err := os.Create(path)
+	if err != nil {
+		return err
+	}
+	defer func() {
+		if closeErr := out.Close(); err == nil {
+			err = closeErr
+		}
+	}()
+
+	compressor := gzip.NewWriter(out)
+	defer func() {
+		if closeErr := compressor.Close(); err == nil {
+			err = closeErr
+		}
+	}()
+
+	writer := tar.NewWriter(compressor)
+	defer func() {
+		if closeErr := writer.Close(); err == nil {
+			err = closeErr
+		}
+	}()
+
+	data := []byte(contents)
+	if err := writer.WriteHeader(&tar.Header{
+		Name: targetName,
+		Mode: 0o600,
+		Size: int64(len(data)),
+	}); err != nil {
+		return err
+	}
+	if _, err := writer.Write(data); err != nil {
+		return err
+	}
+
+	return writer.WriteHeader(&tar.Header{
+		Name:     linkName,
+		Linkname: targetName,
+		Typeflag: tar.TypeLink,
+		Mode:     0o600,
+	})
+}
diff --git a/scripts/build/llama-cpp-build-target_test.sh b/scripts/build/llama-cpp-build-target_test.sh
new file mode 100755
index 000000000000..3d3970b5551e
--- /dev/null
+++ b/scripts/build/llama-cpp-build-target_test.sh
@@ -0,0 +1,26 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+CURDIR=$(dirname "$(realpath "$0")")
+SELECTOR="$CURDIR/../../.docker/llama-cpp-build-target.sh"
+
+assert_target() {
+  local arch=$1
+  local build_type=$2
+  local expected=$3
+  local actual
+
+  actual=$("$SELECTOR" "$arch" "$build_type")
+  if [ "$actual" != "$expected" ]; then
+    echo "FAIL: $arch/$build_type selected $actual, expected $expected"
+    exit 1
+  fi
+}
+
+assert_target amd64 cublas llama-cpp-cpu-all
+assert_target amd64 vulkan llama-cpp-cpu-all
+assert_target amd64 "" llama-cpp-cpu-all
+assert_target arm64 cublas llama-cpp-fallback
+assert_target arm64 "" llama-cpp-cpu-all
+
+echo "PASS: llama.cpp build target preserves CPU variants where supported"