Ternary-Bonsai-8B-gguf
Prism ML Website White Paper Demo & Examples Discord
Params
—
Context
—
Downloads 30d
174 K
Likes
176
Download history
daily snapshots · 89 days
▲ 193 K in the last 30 days (52.6%)
370 K174 K
Oct 12Oct 22Nov 1Nov 10
397 K174 K
Aug 14Sep 12Oct 12Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict 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 run ternary-bonsai-8b-gguf # pin the quantization explicitly $ ollama run ternary-bonsai-8b-gguf-gguf
$ huggingface-cli download prism-ml/Ternary-Bonsai-8B-gguf-GGUF \
Ternary-Bonsai-8B-F16.gguf --local-dir .
$ llama-cli -m Ternary-Bonsai-8B-F16.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/ternary-bonsai-8b-gguf
{
"hf_id": "prism-ml/Ternary-Bonsai-8B-gguf",
"params_b": null,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 174181,
"vram_estimates": [
{ "quant": "GGUF", "gb": 18.5 },
{ "quant": "Q2_0", "gb": 2.9 }
],
"updated_at": "2026-08-14T01:00:43Z"
}
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