qwen3.8-flash-next on strix halo — 91g quant, 56 tok/s, 262k context, receipts included
☆28Sep 24, 2026Updated last month
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☆100Updated 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), …☆95Sep 24, 2026Updated last month
- Kyojin: open-source engine that runs 100 GB-class open models (GLM-5.3, Qwen3.8, DeepSeek V4.1) on one desktop machine. AMD Strix Halo, N…☆234Updated this week
- WiFi connection manager with captive portal for ESP32. Features automatic credential storage, OTA updates, and ESPAsyncWebServer integrat…☆19Dec 30, 2025Updated 10 months ago
- ☆18Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Two-rank tensor-parallel LLM serving over USB4v2 between AMD Strix Halo hosts: a custom Linux thunderbolt stream transport, self-healing …☆17Updated 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…☆224Oct 25, 2026Updated 2 weeks ago
- ☆95Updated this week
- Winning Qwen and DeepSeek setups for AMD Strix Halo: pinned Ansible recipes and matched benchmarks on a 128 GiB Ryzen AI Max+ 395 / Radeo…☆29Updated this week
- Rust LLM inference engine tuned for AMD Strix Halo (gfx1151): a fork of Strata with ggml/llama.cpp-derived HIP kernels. Five models on on…☆39Updated this week
- rust binding for lean4☆12Jul 1, 2023Updated 3 years ago
- Simple Tool Caller for llama.cpp☆11Aug 12, 2024Updated 2 years ago
- Portable vLLM builds with AMD ROCm acceleration for Lemonade☆81Sep 9, 2026Updated 2 months ago
- A small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.☆16Sep 7, 2026Updated 2 months ago
- 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.
- Thompson-mode systems discipline for AI agents. Think first, build bottom-up, brute force until measured, rewrite over patch.☆14Updated this week
- 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…☆52Updated this week
- Program verification with F* course materials☆12Jul 6, 2019Updated 7 years ago
- ☆11Sep 10, 2024Updated 2 years ago
- Local AI harness for coding agents: local-first, any OpenAI-compatible engine or cloud model. Tuned for AMD Strix Halo (Qwen3.8 125B on t…☆38Updated this week
- Zero Knowledge LANGuage in OCaml☆12Jul 15, 2024Updated 2 years ago
- A portable, zero-install Windows tool for loading CAN measurement files BLF MDF MDF4 CSV, decoding signals with or without DBC databases…☆27Updated this week
- AI Agent Service built with FastAPI☆14Aug 20, 2025Updated last year
- Documentation for the on-premise version of PM2 Enterprise☆14Jan 14, 2026Updated 9 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Malware dev tricks: parent PID spoofing. C++ implementation☆12Sep 7, 2022Updated 4 years ago
- Repository for storage of Axon Rapid Response related queries, scripts and more☆10Jul 22, 2025Updated last year
- DeepSeek-V4-Flash inference for AMD Strix Halo☆28Sep 11, 2026Updated last month
- Calculus of Constructions Implementation☆17Dec 20, 2019Updated 6 years ago
- 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-strea…☆53May 10, 2026Updated 5 months ago
- Asynchronous downloads manager library for Nim.☆12Jan 12, 2024Updated 2 years ago
- [Archived] No longer maintained. Run AI coding agents in parallel inside hardened, isolated containers.☆26Sep 30, 2026Updated last month
- Set or toggle multiple monitor's input sources via DDC/CI☆13Mar 1, 2019Updated 7 years ago
- On-device documentation search for agents☆55Nov 1, 2026Updated last week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- 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…☆60Sep 30, 2026Updated last month
- Proving shortest paths with recursive SNARKs☆15Mar 9, 2023Updated 3 years ago
- Utility functions based on Object Pascal's runtime type information (RTTI)☆14Oct 15, 2018Updated 8 years ago
- the unofficial poimandres theme for ghostty terminal☆18Jul 1, 2025Updated last year
- Semantic Skill Space (SSS): Injecting skill embeddings into KV cache for small-model agents to recover skill behavior with lower prompt-c…☆15Mar 2, 2026Updated 8 months ago
- Your paperwork, handled. A Claude-powered personal document and email system on Google Workspace + Supabase.☆23Oct 21, 2026Updated 2 weeks ago
- A small, local-first AI chat workspace for any OpenAI-compatible model. Cache-efficient conversations, MCP tools, web search and persiste…☆37Updated this week
Are these results useful?