{"slug": "calling-all-gpus-help-us-benchmark-sonicboom-v0-0-3", "title": "Calling all GPUs: help us benchmark SonicBoom v0.0.3", "summary": "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.", "body_md": "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\n\nThank you for helping! This issue collects results for v0.0.3 only. It will be locked when\nthe next version's benchmark issue opens; results posted here go into the README community table\nwith your GitHub handle.\n\nSame commit we use: 43fe9c64281, built with CUDA; point LLAMA_BENCH at llama-bench.\n\n4. Run\n\n```\nLLAMA_BENCH=/path/to/llama-bench tools/sb-report.sh \\\n  --gemma /path/to/gemma-4-E4B-it-Q3_K_M.gguf \\\n  --qwen  /path/to/qwen2.5-0.5b-instruct-q4_k_m.gguf\n```\n\n5. Paste\n\nThe whole Markdown block it prints (build info, GPU, golden checks, benchmark tables).\nIf something fails, paste the output anyway — failures on hardware we don't have are the most\nvaluable reports.", "url": "https://wpnews.pro/news/calling-all-gpus-help-us-benchmark-sonicboom-v0-0-3", "canonical_source": "https://github.com/hardenedlinux/SonicBoom/issues/2", "published_at": "2026-10-19 03:47:27+00:00", "updated_at": "2026-10-19 04:20:04.016538+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "ai-infrastructure"], "entities": ["SonicBoom", "Gemma 4 E4B-it-Q3_K_M", "Qwen2.5-0.5B-Instruct-Q4_K_M", "llama-bench", "GitHub", "CUDA"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/calling-all-gpus-help-us-benchmark-sonicboom-v0-0-3", "markdown": "https://wpnews.pro/news/calling-all-gpus-help-us-benchmark-sonicboom-v0-0-3.md", "text": "https://wpnews.pro/news/calling-all-gpus-help-us-benchmark-sonicboom-v0-0-3.txt", "jsonld": "https://wpnews.pro/news/calling-all-gpus-help-us-benchmark-sonicboom-v0-0-3.jsonld"}}