OSS Radar
synchopate/llama-modchip
Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure 64GB CPU at 256K ctx (0 GPUs). Why it matters: helps you run models on your own hardware without an API bill.
GitHub description: 🐋 Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure 64GB CPU at 256K ctx (0 GPUs). SwiGLU-H2, Stockfish-PVS L3 & 13ms Claude Code restore.
Stars
189
Last 24h
+101
Last 7 days
+138est.
Forks
18
Related repos
All llama-modchip alternatives →- project-mayamw00/project-maya+302 stars this week
Run GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard…
- kapitsanace-ai/kapitsa+208est. stars this week
Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai.
- HyperQwensyv-ai/HyperQwen+139 stars this week
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM…
- PolyStratasimplexai-labs/PolyStrata+160est. stars this week
Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith…
Star history
GitHub stars over time. A steeper line means the repo is gaining attention faster.
Daily, since Nov 2, 2026 · 71 → 189
* / est. Estimated: until we have enough daily snapshots for a repo, its gain is total stars ÷ days since creation. Measured numbers replace estimates automatically.
Discussed on Hacker News
Hacker News is a popular tech discussion site. 1 story links to this repo, with 89 upvotes (points) in total.
Llama-modchip: 284B DeepSeek on 64GB RAM, no GPU89 points · 30 comments · Nov 8, 2026Maintainer? Add the badge to your README
Shows your live OSS Radar rank and links back here. Updates hourly.
[](https://ossradar.net/repo/synchopate/llama-modchip)<a href="https://ossradar.net/repo/synchopate/llama-modchip"><img src="https://ossradar.net/badge/synchopate/llama-modchip" alt="Trending on OSS Radar"></a>About llama-modchip
synchopate/llama-modchip is a Python project in the Local LLMs category, created 10 days ago. It has 189 GitHub stars and 18 forks, and gained +138 stars over the last 7 days (early estimate), ranking #6 of 6 Local LLMs repos tracked by OSS Radar this week.
See more trending Local LLMs repos or the top AI repos this week. Looking for something similar? See llama-modchip alternatives.
- Language
- Python
- Category
- Local LLMs
- License
- Apache-2.0
- Created
- Oct 29, 2026
- Last code push
- today (Nov 8, 2026)
- Latest release
- v2.4.0 4 days ago
- AI agents
- apple silicon
- avx512
- Claude Code
- cpu inference
- DeepSeek
- DeepSeek v4
- GGUF
- hpc
- llama.cpp
- local LLM
- mamba2
- mixture of experts
- nemotron
- quantization
- qwen3
- speculative decoding
- stockfish
- zen5
Rising in Local LLMs this week
- Ollamaollama/ollama+754 stars this week
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
- OpenAmikazeekk0/OpenAmika+530 stars this week
OpenAmika: MekaHime's AI companion Amika, open source. Live2D avatar, real-time voice, long-term memory, OpenRouter or Ollama brain.
- DigUpARahim3/DigUp+227 stars this week
Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code.
- MeetilyZackriya-Solutions/meetily+162 stars this week
Privacy-first AI meeting note taker for Windows and macOS. Free, open source (MIT).
- RustingStrataRustingStudio/RustingStrata+141est. stars this week
Pure-Rust MoE inference engine for Qwen3.5/3.6/3.8 GGUF. CPU+GPU hybrid experts, NVRTC CUDA kernels, OpenAI-compatible server.
llama-modchip is #115 of 450 on today's leaderboard.