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.
☆52May 10, 2026Updated 4 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 3 months ago
- Home-enthusiast's guide to fine-tuning 27B+ LLMs on AMD Strix Halo (gfx1151, Ryzen AI MAX+ 395) — the patches and tuning to make Linux ma…☆29Jun 9, 2026Updated 3 months ago
- ☆29Jul 30, 2026Updated 2 months ago
- Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results…☆350Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Portable vLLM builds with AMD ROCm acceleration for Lemonade☆76Sep 9, 2026Updated 3 weeks ago
- ☆533Sep 22, 2026Updated last week
- ☆90Updated this week
- Experimental support for many TTS/STT LLMs wrapped in a Wyoming API for consumption via Homeassistant☆44Sep 13, 2026Updated 2 weeks ago
- This is a mirror of the Strix Halo HomeLab wiki, to browse the wiki click on the link below☆73Aug 31, 2026Updated last month
- ☆29Jun 10, 2026Updated 3 months ago
- Dockernized ComfyUI with PyTorch & flash-attention for gfx1151 (AMD Strix Halo, Ryzen AI Max+ 395), relying on AMD's pre-built and pre-co…☆45Feb 25, 2026Updated 7 months ago
- ☆162Sep 2, 2026Updated last month
- ☆20Sep 4, 2025Updated last year
- 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.
- RDNA-native LLM inference engine in Rust.☆650Updated this week
- Lemonade Pi Agent CLI Plugin☆17Sep 12, 2026Updated 3 weeks ago
- NEW ROCmfp4 format for llama.cpp☆157Jun 13, 2026Updated 3 months ago
- ☆1,972Updated this week
- ☆56Sep 1, 2026Updated last month
- LLM Fine Tuning Toolbox images for Ryzen AI 395+ Strix Halo☆66Sep 12, 2025Updated last year
- ☆256Oct 30, 2025Updated 11 months ago
- Nemotron Speech ASR Docker deployment☆30Jun 7, 2026Updated 3 months ago
- World's first AMD NPU driver for TUXEDO laptops - Enable AI acceleration on Linux☆51Aug 5, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- A high-performance RCCL / NCCL (ROCm Communication Collectives Library) plugin for Thunderbolt 5 that enables GPU-to-GPU communication ac…☆70Sep 16, 2026Updated 2 weeks ago
- Run LLMs on AMD Ryzen™ AI NPUs in minutes; purpose-built and deeply optimized for the AMD NPUs.☆1,922Updated this week
- Fresh builds of llama.cpp with AMD ROCm™ 7 acceleration☆764Updated this week
- Local AI setup for AMD Strix Halo APU - Lemonade + Vulkan + kyuz0☆84Sep 16, 2026Updated 2 weeks ago
- LLM speculative inference server for heterogeneous hardware & consumer GPUs☆2,887Updated this week
- ☆102Mar 8, 2026Updated 6 months ago
- The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)☆801Updated this week
- Student little project to learn API uses and react☆13Nov 15, 2025Updated 10 months ago
- Experimental implementation of DeepSeek v4 flaash in llama.cpp☆24Apr 30, 2026Updated 5 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Causal Parallel Tree Drafting☆228Sep 21, 2026Updated last week
- Run llama.cpp server with Vulkan☆19Aug 5, 2026Updated last month
- This hook integrates with Claude Code to automatically create git checkpoints (snapshots) of your code before any file modifications. It …☆15Jul 6, 2025Updated last year
- Fork of turbo quant tom-tom and TurboQuant KV cache from domwox☆31Jul 7, 2026Updated 2 months ago
- Mistral Vibe rewritten in Rust by Devstral 2☆21Dec 23, 2025Updated 9 months ago
- ☆43Apr 26, 2026Updated 5 months ago
- A converter for transferring gguf Q4_0, Q4_1 to FLM Q4NX☆41Sep 24, 2026Updated last week