OSS Radar
prabanta-dev/janas
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.
GitHub description: 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 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
Stars
332
Last 24h
+11
Last 7 days
+77est.
Forks
21
Star history
GitHub stars over time. A steeper line means the repo is gaining attention faster.
Last 2 hours · +8 stars
Daily, since Oct 13, 2026 · 321 → 332
* / 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 214 upvotes (points) in total.
Janas: Run LLMs larger than RAM by streaming experts from SSD214 points · 86 comments · Oct 12, 2026Maintainer? Add the badge to your README
Shows your live OSS Radar rank and links back here. Updates hourly.
[](https://ossradar.net/repo/prabanta-dev/janas)<a href="https://ossradar.net/repo/prabanta-dev/janas"><img src="https://ossradar.net/badge/prabanta-dev/janas" alt="Trending on OSS Radar"></a>About janas
prabanta-dev/janas is a C project in the Local LLMs category, created 24 days ago. It has 332 GitHub stars and 21 forks, and gained +77 stars over the last 7 days (early estimate), ranking #3 of 6 Local LLMs repos tracked by OSS Radar this week.
See more trending Local LLMs repos or the top AI repos this week.
- Language
- C
- Category
- Local LLMs
- Created
- Sep 20, 2026
- Last code push
- today (Oct 14, 2026)
- Latest release
- v2026.10.13 today
- avx2
- c
- cpu-inference
- gguf
- inference-engine
- linux
- llm
- local-llm
- mixture-of-experts
- moe
- nvme
- quantization
- qwen3
- simd
- speculative-decoding
- vulkan
Similar rising repos
Rewrites AI drafts so they read like a person wrote them — runs locally, keeps the facts. Why it matters: helps you run models on your own hardware without an API bill.
- 1nikitas/NIKA_desktop+28est.
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+741est.
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+21est.
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.
- syv-ai/HyperQwen+42est.
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer… Why it matters: useful plumbing for shipping LLM-powered features.
- ARahim3/DigUp+1.4kest.
Search your Mac by what's in your files: photos, PDFs, recordings, videos and code. On-device, built on Google DeepMind's EmbeddingGemma 2. Why it matters: helps you run models on your own hardware without an API bill.