prism-ml / text-generation updated 3 months ago

Ternary-Bonsai-8B-gguf

Prism ML Website    White Paper    Demo & Examples    Discord

Params
Context
Downloads 30d
392 K
Likes
155
Commercial use: allowed apache-2.0 Not gated GGUF View on Hugging Face ↗

Download history

daily snapshots · 39 days
▲ 178 K in the last 30 days (82.7%)
397 K181 K
Aug 14Aug 27Sep 9Sep 21

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
Ternary-Bonsai-8B-PQ2_0.gguf Q2_0 2.2 GB 2.9 GB ✅ Runs comfortably
Ternary-Bonsai-8B-Q2_0_g64.gguf Q2_0_G64 2.3 GB 3.0 GB ✅ Runs comfortably
Ternary-Bonsai-8B-F16.gguf GGUF 16.4 GB 18.5 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub
~ · ollama · GGUF
$ ollama run ternary-bonsai-8b-gguf

# pin the quantization explicitly
$ ollama run ternary-bonsai-8b-gguf-gguf
est. VRAM 18.5 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence
apache-2.0
First seen on the Hub
2026-04-18
Training datasets
undisclosed
Added to our catalog
2026-08-14
Compare with any text-generation model