OSS Radar
peonist-ai/halogen-flash-server
The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151). Why it matters: helps you run models on your own hardware without an API bill.
GitHub description: The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)
Stars
961
Last 24h
+1
Last 7 days
+7est.
Forks
67
Star history
GitHub stars over time. A steeper line means the repo is gaining attention faster.
Daily, since Oct 13, 2026 · 960 → 961
* / est. Estimated: until we have enough daily snapshots for a repo, its gain is total stars ÷ days since creation. Measured numbers replace estimates automatically.
Maintainer? Add the badge to your README
Shows your live OSS Radar rank and links back here. Updates hourly.
[](https://ossradar.net/repo/peonist-ai/halogen-flash-server)<a href="https://ossradar.net/repo/peonist-ai/halogen-flash-server"><img src="https://ossradar.net/badge/peonist-ai/halogen-flash-server" alt="Trending on OSS Radar"></a>About halogen-flash-server
peonist-ai/halogen-flash-server is a Shell project in the Local LLMs category, created 49 days ago. It has 961 GitHub stars and 67 forks, and gained +7 stars over the last 7 days (early estimate), ranking #7 of 7 Local LLMs repos tracked by OSS Radar this week.
See more trending Local LLMs repos or the top AI repos this week.
- Language
- Shell
- Category
- Local LLMs
- Created
- Aug 26, 2026
- Last code push
- today (Oct 14, 2026)
- amd
- gfx1151
- gpu-inference
- hip
- inference-engine
- llm
- llm-serving
- local-llm
- long-context
- mixture-of-experts
- openai-api
- qwen
- qwen3
- radeon
- rocm
- ryzen-ai
- speculative-decoding
- strix-halo
Similar rising repos
- prabanta-dev/janas+21est.
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all… Why it matters: helps you run models on your own hardware without an API bill.
- ARahim3/kaggle-tpu-lab+101est.
Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~165 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s)… Why it matters: relevant if AI is part of your coding workflow.
- 1nikitas/NIKA_desktop+25est.
Native AI assistant for macOS, built with SwiftUI and llama.cpp. Run local LLMs offline, work with PDFs, and create custom AI assistants. Optional… Why it matters: helps you run models on your own hardware without an API bill.
- mw00/project-maya+737est.
Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server… Why it matters: useful plumbing for shipping LLM-powered features.
- maziyarpanahi/openmed+14est.
Local-first healthcare AI: clinical NER and HIPAA PII de-identification on hardware you control. 2,200+ medical models, 35 model-backed PII… Why it matters: helps you run models on your own hardware without an API bill.
- vllm-project/vllm+7est.
A high-throughput and memory-efficient inference and serving engine for LLMs. Why it matters: useful plumbing for shipping LLM-powered features.