llama-modchip alternatives

synchopate/llama-modchip (189 stars, +138 this week): 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).

Below are 5 other repos tracked by OSS Radar that share GitHub topics with llama-modchip: 1 from Local LLMs sharing at least two about what they do, and 4 from other categories sharing at least three topics about what they do (platform, language and framework tags don't count), two of them niche rather than broad ones like llm, ordered by how closely their topics overlap (rarer shared topics count more), then by stars gained in the last 7 days. Topic overlap means a similar problem space, not a drop-in replacement, so check each project's README.

1. project-mayamw00/project-maya
+302/wk
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…
2.7k stars · Cuda · LLM tooling · shared topics: DeepSeek, DeepSeek v4, GGUF, local LLM, mixture of experts, quantization · project-maya alternatives
2. kapitsanace-ai/kapitsa
+208/wkest.
Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai.
700 stars · C++ · LLM tooling · shared topics: apple silicon, llama.cpp, local LLM, nemotron, speculative decoding · kapitsa alternatives
3. HyperQwensyv-ai/HyperQwen
+139/wk
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM…
2.6k stars · Python · LLM tooling · shared topics: local LLM, quantization, qwen3, speculative decoding · HyperQwen alternatives
4. PolyStratasimplexai-labs/PolyStrata
+160/wkest.
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…
921 stars · C++ · LLM tooling · shared topics: GGUF, local LLM, mixture of experts, speculative decoding · PolyStrata alternatives
5. RustingStrataRustingStudio/RustingStrata
+141/wkest.
Pure-Rust MoE inference engine for Qwen3.5/3.6/3.8 GGUF. CPU+GPU hybrid experts, NVRTC CUDA kernels, OpenAI-compatible server.
141 stars · Rust · shared topics: GGUF, llama.cpp, local LLM, mixture of experts · RustingStrata alternatives

More rising Local LLMs repos

Only 5 tracked repos share at least two GitHub topics with llama-modchip, so here are the Local LLMs repos gaining the most stars this week. They sit in the same category but don't share its topics, so treat them as related projects rather than alternatives.

Ollama +754/wk: Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
OpenAmika +530/wk: OpenAmika: MekaHime's AI companion Amika, open source. Live2D avatar, real-time voice, long-term memory, OpenRouter or Ollama brain.
DigUp +227/wk: Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code.
Meetily +162/wk: Privacy-first AI meeting note taker for Windows and macOS. Free, open source (MIT).

llama-modchip alternatives

1. project-mayamw00/project-maya

2. kapitsanace-ai/kapitsa

3. HyperQwensyv-ai/HyperQwen

4. PolyStratasimplexai-labs/PolyStrata

5. RustingStrataRustingStudio/RustingStrata

More rising Local LLMs repos