AI Max+ 395 acceleration: measured heterogeneous GPU PD and asynchronous fused-layer pipeline experiments with RTX 3060.
-
Updated
Sep 10, 2026 - Python
#
rtx-3060
Here are 11 public repositories matching this topic...
Pinned, hash-verified Comfy-Org MiniMax H3 ComfyUI workflows for T2V, I2V and R2V, with RTX 3060 benchmark evidence.
image-to-video text-to-video ai-video comfyui comfyui-workflow rtx-3060 reference-to-video workflow-json minimax-h3
-
Updated
Aug 23, 2026
DeepSeek-R1 7B INT4 at 69.3 tok/s on a $300 RTX 3060. Faster than llama.cpp, vLLM, and NVIDIA TensorRT-LLM. Is one developer + Ai really better than the entire industry?
inference-engine cachyos local-llm speculative-decoding deepseek-r1 cuda-optimization rtx-3060 w4a16
-
Updated
May 19, 2026 - Python
Unofficial FreeToken fork: on one RTX 3060 12 GB, a 35B MoE at 250k of context or gpt-oss-120b; Flash-Next 125B on two. Half the RAM, image input. Runs on Turing: RTX 2060, RTX 20 series, sm_75.
moe offloading inference-engine vram multimodal mixture-of-experts pipeline-parallelism wsl2 long-context local-llm llm-inference speculative-decoding qwen3 consumer-gpu gpt-oss gpt-oss-120b rtx-3060 freetoken nvidia-turing rtx-2060
-
Updated
Sep 10, 2026 - Python
Experimental open RTX 3060 driver research for macOS Tahoe — safe probe first
-
Updated
Sep 4, 2026 - Python
Reproducible single-system evaluation of Qwen3.8-27B on an RTX 3060 12 GB: long-context inference, KV-cache optimization, Windows/WSL2, and Codex integration.
-
Updated
Sep 7, 2026 - Python
Getting LTX-2.5 and MiniMax-H3 running reliably on a 12GB card in ComfyUI — real bugs found and fixed, not just a config dump
-
Updated
Sep 9, 2026 - Python
🚀 A high-performance, GPU-accelerated (NVIDIA CUDA 13.2) Dev Container for Machine Learning and Deep Learning. Features Python 3.12 (uv), Node 22 (fnm), JupyterLab, and Docker-in-Docker, keeping your host system 100% clean.
docker machine-learning deep-learning docker-compose pytorch jupyterlab vscode-devcontainer rtx-3060
-
Updated
Jun 23, 2026 - Dockerfile
Knowledge distillation from GPT-5.5-xhigh into Qwen2.5-1.5B-Instruct: bf16 LoRA trained on a 6GB RTX 3060, served as a containerized OpenAI-compatible API (FastAPI + llama.cpp) with a streaming React chat UI. 570-prompt dataset across 10 categories, held-out perplexity evaluation, GGUF quantized deployment.
react docker pytorch lora quantization knowledge-distillation fine-tuning sft vite fastapi cpu-inference llm llama-cpp qwen gguf openai-compatible rtx-3060
-
Updated
Aug 10, 2026 - Python
Add this topic to your repo
To associate your repository with the rtx-3060 topic, visit your repo's landing page and select "manage topics."