cd /news/ai-tools/calling-all-gpus-help-us-benchmark-s… · home › topics › ai-tools › article
[ARTICLE · art-152663] src=github.com ↗ pub= topic=ai-tools verified=true sentiment=· neutral

Calling all GPUs: help us benchmark SonicBoom v0.0.3

The SonicBoom project is soliciting community GPU benchmark results for version v0.0.3, asking contributors to build commit 43fe9c64281 with CUDA and run its tools/sb-report.sh script against Gemma 4 E4B-it-Q3_K_M and Qwen2.5-0.5B-Instruct-Q4_K_M model files using llama-bench. Results posted to the issue will be added to the README community table under each contributor's GitHub handle, and the issue will be locked when the next version's benchmark issue opens. The project said failures on hardware it does not have are the most valuable reports.

by read1 min views1 publishedOct 19, 2026
Calling all GPUs: help us benchmark SonicBoom v0.0.3
Image: Michielbdejong (auto-discovered)

You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert

Thank you for helping! This issue collects results for v0.0.3 only. It will be locked when the next version's benchmark issue opens; results posted here go into the README community table with your GitHub handle.

Same commit we use: 43fe9c64281, built with CUDA; point LLAMA_BENCH at llama-bench.

  1. Run
LLAMA_BENCH=/path/to/llama-bench tools/sb-report.sh \
  --gemma /path/to/gemma-4-E4B-it-Q3_K_M.gguf \
  --qwen  /path/to/qwen2.5-0.5b-instruct-q4_k_m.gguf
  1. Paste

The whole Markdown block it prints (build info, GPU, golden checks, benchmark tables). If something fails, paste the output anyway — failures on hardware we don't have are the most valuable reports.

── more in #ai-tools 4 stories · sorted by recency
── more on @sonicboom 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/calling-all-gpus-hel…] indexed:0 read:1min 2026-10-19 · —