edge-cpu-gguf-tuner
Evidence-first, offline tuning of llama.cpp GGUF inference on CPU and constrained edge hosts. Inspects CPU topology, renders compatible benchmark plans, optionally runs an explicitly supplied local llama-bench, ranks pp/tg/pg results with variance-aware confidence, verifies output gates, and renders
as observed 2026-09-08T10:18:19.295Z- Identifier
edge-cpu-gguf-tuner- Source
- ClawHub
- Version observed
- 1.2.5
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-08-28T22:54:49.073Z
- Observations recorded
- 4
- Installs (reported upstream)
- 2
- Weekly downloads (upstream)
- 1,124
Observation history
2026-09-08T10:18:19.295Z
Fields that differed: changelog latestVersion topics
| Field | Before | After |
|---|---|---|
changelog |
"edge-cpu-gguf-tuner 1.2.4\n\n- Removed the file skill-card.md.\n- No user-facing changes to the workflow or documentation.\n- All features and usage instructions remain unchanged. | "edge-cpu-gguf-tuner 1.2.5 changelog:\n\n- Removed the file: skill-card.md.\n- No other changes to code or functionality." |
latestVersion |
"1.2.4" | "1.2.5" |
topics |
["cpu-inference","gguf","llama-cpp","performance"] | ["cpu-inference","development","gguf","llama-cpp","performance"] |
2026-09-07T09:39:20.406Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"1.2.2: make cold-install usage robust when executable bits are not preserved; document sh entrypoint invocation and verify the installed self-test." | "edge-cpu-gguf-tuner 1.2.4\n\n- Removed the file skill-card.md.\n- No user-facing changes to the workflow or documentation.\n- All features and usage instructions remain unchanged. |
latestVersion |
"1.2.2" | "1.2.4" |
2026-09-06T09:04:43.486Z
Fields that differed: changelog description latestVersion summary topics
| Field | Before | After |
|---|---|---|
changelog |
"README-only documentation: complete functionality, usage, permissions, security/privacy, related emojis, and corrected TREE-SHA256-v1 verification excluding registry-generated met | "1.2.2: make cold-install usage robust when executable bits are not preserved; document sh entrypoint invocation and verify the installed self-test." |
description |
"Tune llama.cpp GGUF inference on CPU-only / edge boxes (1-4 cores, low RAM) for maximum tokens/sec. Complements GPU-oriented tuners. Contains measured, counterintuitive CPU-specif | "Evidence-first, offline tuning of llama.cpp GGUF inference on CPU and constrained edge hosts. Inspects CPU topology, renders compatible benchmark plans, optionally runs an explici |
latestVersion |
"1.1.9" | "1.2.2" |
summary |
"Tune llama.cpp GGUF inference on CPU-only / edge boxes (1-4 cores, low RAM) for maximum tokens/sec. Complements GPU-oriented tuners. Contains measured, counterintuitive CPU-specif | "Evidence-first, offline tuning of llama.cpp GGUF inference on CPU and constrained edge hosts. Inspects CPU topology, renders compatible benchmark plans, optionally runs an explici |
topics |
["automation","cpu-inference","gguf","llama-cpp","performance"] | ["cpu-inference","gguf","llama-cpp","performance"] |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.