Bonsai 1.7B ternary model at 442T/s on M4 Max
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
We took a recently released Bonsai 1.7B ternary model from PrismML (https://github.com/PrismML-Eng/Bonsai-demo) and ran our agentic evolution search on it for 6 hours to optimize the Metal kernels. The search was fully autonomous.Measured against unmodified upstream llama.cpp at the same Bonsai/Q2_0 commit, same M4 Max:- tg128: 309.82 → 442.42 t/s (+42.0%)- pp512: 4250.32 → 4622.63 t/s (+8.8%)
HN · launched May 4, 2026 · 13 upvotes (top 35%) · 0 views
Niche: large language models · 191 launches, 4 in the last 7 days ▼ -33% · Explore this niche →
Category and tags
- Horizontal
- Model & infra
- Developer
- AI-native
- Hobby / open-source project
Visit website ↗ Source listing ↗
More like this: all 191 launches in large language models →
Could you build this?
No Engineering ultra-fast ternary LLM inference on Apple Silicon involves writing custom low-level Metal Shading Language (MSL) kernels, threadgroup memory management, and SIMD-level matrix multiplication optimizations.
What it would actually take: This requires modifying the llama.cpp or MLX runtime with hand-tuned Metal Compute Shaders (MSL) specifically designed for 1.58-bit / ternary weight packing. The developer needs deep GPU microarchitecture expertise to optimize SIMD-group matrix multiply-accumulate (mma) instructions, utilize Apple Silicon unified memory caching, and minimize bandwidth bottlenecks through register pressure tuning and automated kernel search loops.
Discussion
3 comments analyzed.
Competitors
Other products that read as similar to this one : 56 launches clear the similarity bar, closest 8 shown.
Attention rank: #19 of 57 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 179 days after the earliest competitor.
- bonsai2-small-gpu · github · 2026-09-19 · 54 upvotes · similarity 0.57
- lmstudio-prism-bonsai · github · 2026-09-21 · 9 upvotes · similarity 0.55
- ninfer-ternary-bonsai-ada · github · 2026-09-20 · 23 upvotes · similarity 0.54
- Running PrismML's Bonsai inside DRAM by breaking DDR4 timing rules · hn · 2026-07-23 · 23 upvotes · similarity 0.52
- Bonsai-27B-NInfer · github · 2026-09-24 · 10 upvotes · similarity 0.52
- mlxfast-bonsai2-27b-engine · github · 2026-09-24 · 30 upvotes · similarity 0.49
- OrcaBonsai-27B-Uncensored · github · 2026-09-18 · 526 upvotes · similarity 0.47
- Qwen3.8-Max · ph · 2026-08-03 · 276 upvotes · similarity 0.38
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.