arizqi/

cpubrrr

GitHub

Frontier-class LLM inference on a laptop CPU — gpt-oss:20b at ~110 tok/s on Apple M4 Max, 7.5x llama.cpp, no GPU. From-scratch NEON/SME kernels in Rust.

54stars

5forks

3issues

Apache-2.0license

2026since

Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap

vllm-project/

vllm

▲ 704/wk

A high-throughput and memory-efficient inference and serving engine for LLMs

88k20kPython

ollama/

ollama

▲ 640/wk

Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

178k17kGo

hiyouga/

LlamaFactory

▲ 162/wk

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

74k9.0kPython

unslothai/

unsloth

▲ 524/wk

Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, GLM and other models.

70k6.3kPython

rtk-ai/

rtk

▲ 998/wk

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

75k4.7kRust

Hmbown/

CodeWhale

▲ 245/wk

Open-source, community-driven agent harness

40k3.5kRust

Comparecpubrrr vs vllm cpubrrr vs ollama cpubrrr vs LlamaFactory

SharePost on X LinkedIn