vLLM Qwen 3.6-27B (AWQ-INT4) + DFlash speculative decoding on AMD Strix Halo (gfx1151 iGPU, 128 GB UMA, ROCm 7.13). 24.8 t/s single-stream, vision, tool calling, 256K context, OpenAI-compatible, Docker. Matches DGX Spark FP8+DFlash+MTP at a third of the cost. No CUDA.
☆53May 10, 2026Updated 5 months ago
Alternatives and similar repositories for vllm-awq4-qwen
Users that are interested in vllm-awq4-qwen are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- vLLM + Qwen3.6-27B (BF16) OpenAI-compatible inference server on AMD Strix Halo (Ryzen AI Max+ 395, gfx1151). Vision input, 256K context, …☆18Apr 26, 2026Updated 5 months ago
- Random AI notes for working with local models or playing around with random machine learning bits.☆64Jun 7, 2026Updated 4 months ago
- ☆94Oct 1, 2026Updated 3 weeks ago
- Portable vLLM builds with AMD ROCm acceleration for Lemonade☆80Sep 9, 2026Updated last month
- Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results…☆362Oct 3, 2026Updated 2 weeks ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆29Jul 30, 2026Updated 2 months ago
- Container toolbox that runs llama.cpp with AMD ROCm and NVIDIA CUDA in one build, for inference on two GPUs☆20Oct 16, 2026Updated last week
- A Deepseek V4 Flash 0731 / Vision Exp VLLM stack☆26Sep 24, 2026Updated 3 weeks ago
- ☆90Updated this week
- LLM inference in C/C++☆240Updated this week
- Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI +…☆82Updated this week
- CIRU llama.cpp runtime for Qwen3.8-Flash-CIRU-STRIX-IU4 on AMD Strix Halo☆21Sep 28, 2026Updated 3 weeks ago
- LLM inference in C/C++☆42Updated this week
- The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)☆1,056Updated this week
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- vLLM inference solutions for NVIDIA GB10 (DGX Spark, sm121) — KIMI-K3 B12X_MLA + DSpark, GLM-5.2☆67Sep 30, 2026Updated 3 weeks ago
- ENGRAFT: write facts into an LLM's n-gram (Engram) memory table as a removable overlay: 100 facts in a 9 MB file, no weights touched, ver…☆57Sep 30, 2026Updated 3 weeks ago
- RDNA-native LLM inference engine in Rust.☆727Updated this week
- Linux driver for the embedded controller on the Sixunited AXB35-02 board.☆79Aug 20, 2026Updated 2 months ago
- ☆2,003Updated this week
- LLM Fine Tuning Toolbox images for Ryzen AI 395+ Strix Halo☆66Sep 12, 2025Updated last year
- Dockernized ComfyUI with PyTorch & flash-attention for gfx1151 (AMD Strix Halo, Ryzen AI Max+ 395), relying on AMD's pre-built and pre-co…☆46Feb 25, 2026Updated 7 months ago
- The Open Source Strix Halo AI engine. Qwen 3.8 Flash Next Q4_K_XL: 1,801.01 pp, 73.17 tg single user, 194.37 tok/s 8 users; Qwen 3.8 27B…☆849Updated this week
- RocM Optimized ComfyUI nodes☆52Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆29Jun 10, 2026Updated 4 months ago
- GPU + XDNA2 NPU inference for AMD Strix Halo (gfx1151): Qwen3.6-35B-A3B, Qwen3.8-27B and Qwen3.8 Flash-Next. NPU prefill +9% to +28%, MTP…☆74Updated this week
- Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; port…☆217Oct 9, 2026Updated 2 weeks ago
- Augmentor Agent Desktop and Browser. Public source under MIT with Augmentor Resale Restriction: free use and modification; resale require…☆25Updated this week
- Lemonade Pi Agent CLI Plugin☆16Sep 12, 2026Updated last month
- NEW ROCmfp4 format for llama.cpp☆158Jun 13, 2026Updated 4 months ago
- Production-speed compact Dynamic Memory Sparsification (DMS) for KV cache compression☆27May 6, 2026Updated 5 months ago
- LLM inference engine written from scratch in HIP for AMD Strix Halo (gfx1151) and Qwen3.8-Flash-Next - ~50 tokens/s out to 492k context☆72Updated this week
- Codeberg fork of StillDeadcode / vllm-radiance which is a custom vllm tuned for R9700 GPU's☆128Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- DGX Spark research and tests - containers, benchmarks, and investigation notes for running models on GB10 (SM 12.1)☆28Aug 6, 2026Updated 2 months ago
- A fast diffusion model engine for image generation and editing.☆36Updated this week
- WMMA GEMM in ROCm for RDNA GPUs☆19Sep 1, 2026Updated last month
- Run LLMs on AMD Ryzen AI NPU (Linux)☆30Mar 29, 2026Updated 6 months ago
- ☆56Sep 1, 2026Updated last month
- LLM inference in C/C++☆28Updated this week
- Hermes + Honcho + GBrain integration guide☆35May 29, 2026Updated 4 months ago