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 13 models compared in Q4_K_M. LLMs bigger than your
- Stars
- 459
- Forks
- 36
- Open issues
- 6
- Last push
- today
About janas
janas is a free, open-source LLM chat app by prabanta-dev, written mainly in C. 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. It has 459 GitHub stars and 36 forks, and was last updated today. It's released under the GPL-3.0 license, a standard open-source license.
- License
- GPL-3.0
- Language
- C
- Stars
- 459
- Last update
- today
- Runs on Mac
- Not stated
- GPU
- Not stated
- Paid API key
- Not required
- Self-hostable
- Not stated
Similar free tools
llamafile26k stars · Distribute and run LLMs with a single file.
local-deep-research9.4k stars · ~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encryp
MTPLX2.6k stars · The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple
ml-engineering20k stars · Machine Learning Engineering Open Book
Open-LLM-VTuber14k stars · Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D avatar running locally across platforms
project-maya1.4k stars · Project Maya - run GLM-5.3-Flash (321B MoE) and DeepSeek-V4.1-Flash-1017 (748B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenA
janas FAQ
Is janas free?
Yes. janas is open source and free to use. It's released under the GPL-3.0 license, a standard open-source license.
Does janas run on a Mac?
The project doesn't say. Check its installation guide before you start.
Does janas need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is janas still maintained?
Yes. It was last updated today and has 6 open issues on GitHub.
What are alternatives to janas?
Similar free, open-source tools include llamafile, local-deep-research, MTPLX, ml-engineering.