llama-optimize

Automating llama.cpp LLM parameter optimization for highest speed/best fit using Morris/Taguchi DoE sweeps.

bigattichouse/llama-optimize

View on GitHub ↗

Automating llama.cpp LLM parameter optimization for highest speed/best fit using Morris/Taguchi DoE sweeps.

llama-optimize grew +3.2% in the last 30 days, ranks 295th of 343 in Inference Optimization, last commit 37 days ago.

Star trajectory

63 days tracked
2026-09-1996 stars today2026-11-22
Momentum

+3.2% in 30d, above the Inference Optimization median of +1.6%.

Maintenance

Last commit 37 days ago, staler than the median of 16d.

How it compares in Inference Optimization

llama-optimize
96
stars
+3.2% 30d
commit 37 days ago
Inference Optimization median
242
stars
+1.6% 30d
commit ~16d ago
Leader · supertonic
13.8k
stars
-0.1% 30d
commit 74 days ago

Ranked 295th of 343 by stars.

Ranked by shared tags, then keywords, then stars
  1. TokenSpeed is a speed-of-light LLM inference engine.

    +176 (+6.4%) in 30d · Committed today · Python · MIT

    Shares Local Runtime / Inference Engine, Inference Optimization

  2. Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4…

    +962 (+243%) in 30d · Committed 3d ago · C++ · MIT

    Shares Local Runtime / Inference Engine, Inference Optimization

  3. The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with…

    +66 (+5.6%) in 30d · Committed 51d ago · Python · Apache-2.0

    Shares Local Runtime / Inference Engine, Inference Optimization

  4. Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp…

    +425 (+65%) in 30d · Committed today · C++ · Apache-2.0

    Shares Inference Optimization, Local Runtime / Inference Engine

  5. llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

    +231 (+36%) in 30d · Committed 3d ago · C++ · GPL-3.0

    Shares Local Runtime / Inference Engine, Inference Optimization

  6. a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features…

    +34 (+7.5%) in 30d · Committed today · C++ · Apache-2.0

    Shares Local Runtime / Inference Engine, Inference Optimization

  7. Strata fork: Qwen3.8-Flash-Next 125B MoE in NVFP4 on one RTX 20-50 card (12 GB+) and 64 GB of RAM or more…

    +73 (+39%) in 30d · Committed today · C++ · MIT

    Shares Local Runtime / Inference Engine, Inference Optimization

  8. Optimized SGLang runtime for Qwen3.8-27B FP8 with DFlash2 and Qwen3.8 Flash-Next NVFP4 with FR-Spec on one…

    +31 (+18%) in 30d · Committed today · Python · Apache-2.0

    Shares Local Runtime / Inference Engine, Inference Optimization

  9. Kindi 0.6.1: fast local LLM inference on low-cost GPUs and CPUs. DeepSeek-V4.1-Flash (552B) at 18.7 tok/s on…

    Committed 5d ago · Python · AGPL-3.0

    Shares Local Runtime / Inference Engine, Inference Optimization

  10. WeeLLM runs large diffusion models with as little as 4 GB of VRAM, without any quantization. It dynamically…

    +42 (+36%) in 30d · Committed 13d ago · Python

    Shares Local Runtime / Inference Engine, Inference Optimization

Language
Python
License
MIT License
Contributors
4
Forks
4
Watchers
1
Open issues
3
Releases
0
Created
2026-07-10
Stars this week
+1

You've seen where llama-optimize stands today.

Get the moves before everyone else: the 5 Inference Optimization repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain llama-optimize?

Claim this page to add your own call-to-action.

Claim this page