swellweb / reame
CPU-first LLM inference server on llama.cpp. Runs useful models on free-tier ARM boxes; rewriting the input made it ~6x faster and more accurate than tuning the engine. MIT, benchmarks and failures included.
Why this job: says: llama.cpp, inference server, llm inference; topics: llama-cpp, local-llm, gguf, inference, edge-ai
What it does
These aren't just marketing claims; they are measured. Running Bonsai-8B (PrismML's ternary flagship) against PrismML's own llama.cpp fork on the same hardware, using identical prompts and clean environments:
Get started
git clone https://github.com/swellweb/reame
cd reame && ./build.sh - Maintenance
- Active
- Last commit 28 days ago
- Stars
- 114
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- 2 systems
- Mac, Linux
- Latest version
- v2.0.0
- Released 3 months ago
- Built with
- C++
- 76% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 0% closed
- 5 still open
- Pull requests
- 6 merged
- 0 waiting
- Releases
- 8
- 8 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| vladimirrott / mojo-dllm | 495 | 4 days ago | Apache-2.0 | No downloads |
| Helldez / BigMoeOnEdge | 734 | yesterday | Apache-2.0 | Mac, Windows, Linux |
| AtomicBot-ai / atomic-agent | 3,340 | 12 days ago | MIT | Mac, Linux |
More: download files, languages, topics and project record
Download files, v2.0.0
- Mac1 file, 9 downloads
- Linux2 files, 26 downloads
Languages
- C++ 76%
- Python 19%
- CMake 2%
- JavaScript 2%
Topics
- arm
- cpu
- edge-ai
- gguf
- inference
- kv-cache
- llama-cpp
- llm
- local-llm
- openai-api
- prompt-compression
- self-hosted
Project record
- JobLocal LLMs
- StatusListed
- Commits133
- Forks10
- Watching0
- Stars in 28 days0
- CreatedJul 6, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026