qwen3.8-flash-next on strix halo — 91g quant, 56 tok/s, 262k context, receipts included
☆26Sep 24, 2026Updated 3 weeks ago
Alternatives and similar repositories for haloq38flash
Users that are interested in haloq38flash are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 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☆67Updated this week
- Reproducible, evidence-backed llama.cpp serving recipes for Strix Halo class machines — annotated parameters, ▏ multi-witness results, a…☆21Oct 3, 2026Updated 2 weeks ago
- Rulith Inference, formerly Strix Llama. Serving a 125B MoE model fast on one AMD Strix Halo machine, on Windows: a patched llama.cpp, a m…☆37Updated this week
- WiFi connection manager with captive portal for ESP32. Features automatic credential storage, OTA updates, and ESPAsyncWebServer integrat…☆19Dec 30, 2025Updated 9 months ago
- Atlas Inference is a dependency free lightweight inference engine meant to run LLMs on YOUR compute seamlessly. Supports GB10 and Strix H…☆35Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Winning Qwen and DeepSeek setups for AMD Strix Halo: pinned Ansible recipes and matched benchmarks on a 128 GiB Ryzen AI Max+ 395 / Radeo…☆22Oct 6, 2026Updated 2 weeks ago
- 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
- Portable optimized ROCm and Qwen3.8-27B setup for AMD Strix Halo☆83Sep 16, 2026Updated last month
- Kyojin: the Yamz inference engine for AMD Strix Halo (ROCm, gfx1151), built on ExLlamaV3. Runs 300B-class MoE models on one 128 GB mini P…☆194Updated this week
- A native desktop utility that batch converts bloated office files (.docx, .pdf, .pptx) into token-efficient Markdown to supercharge your …☆24Updated this week
- llama.cpp fork tuned for Qwen 3.8 Flash-Next on AMD Strix Halo — RDNA3.5 kernel patches, true QSA sparse gather, working MTP, 27 GB engra…☆50Updated this week
- Browser SSH over Tailscale with encrypted credentials, tmux sessions, and tiled terminal groups☆15Updated this week
- llama.cpp modified to work with Strix Halo + dGPU as an accelerator, Dual Strix Halo Machines, or both☆51Updated this week
- 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…☆834Updated this week
- 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.
- Coding stack built completely on local models☆21Aug 22, 2026Updated last month
- Your paperwork, handled. A Claude-powered personal document and email system on Google Workspace + Supabase.☆12Updated this week
- High-performance Lemonade alternative for AMD Strix Halo & Radeon — latest MoE models (Ling-3.0-Flash, Qwen 3.8 Flash Next, Ornith 1.5), …☆90Sep 24, 2026Updated 3 weeks ago
- A Unix-like shell for microcontrollers and PCs: users, files, .tdsh scripts, Wi-Fi and Ethernet, SSH/SFTP, FTP, SMB mounts, SD card. Test…☆15Updated 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 last week
- ☆14Sep 8, 2026Updated last month
- Downloader for large model files from services that hand out expiring signed URLs — HuggingFace and Civitai in particular.☆23Sep 29, 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 2 weeks ago
- rust binding for lean4☆11Jul 1, 2023Updated 3 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Simple Tool Caller for llama.cpp☆11Aug 12, 2024Updated 2 years ago
- ☆36Aug 4, 2026Updated 2 months ago
- WMMA GEMM in ROCm for RDNA GPUs☆18Sep 1, 2026Updated last month
- Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI +…☆82Updated this week
- 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…☆31Jun 9, 2026Updated 4 months ago
- The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)☆1,018Updated this week
- Qwen3.8-Flash-Next on 2× RTX 3090: with 128 GB RAM up to 4,191 tok/s prefill · 111.5 tok/s decode (131K prompt), full 256K window at 2,86…☆119Updated this week
- ☆13Dec 20, 2017Updated 8 years ago
- Formalization of complexity theory☆29Oct 11, 2026Updated last week
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants☆37Sep 28, 2026Updated 3 weeks ago
- ☆28Oct 9, 2026Updated last week
- Watch all Kubernetes Resources☆16Jun 16, 2026Updated 4 months ago
- OCaml bindings to the number theory library PARI/GP☆12Jan 11, 2025Updated last year
- Development monorepo for Hex: verified computational algebra in Lean 4 (polynomial factoring, LLL, and friends). Released aggregate: http…☆22Updated this week
- A skill to avoid writing AI-like texts you can install in your best AI tool☆31Sep 26, 2026Updated 3 weeks ago
- a lightning-fast, crash-proof search engine aggregator built in Rust. Focused on memory efficiency, safe character slicing, and high-per…☆17Oct 3, 2026Updated 2 weeks ago