Ternary-Bonsai-2-2B-gguf
A 2B-class vision-language model with ternary transformer weights, for llama.cpp (CUDA, Metal, CPU).
Params
2.0 B
Context
—
Downloads 30d
994 K
Likes
53
Download history
tracking started — chart appears after 7 days of snapshots (2 recorded)994 K downloads in the last 30 days
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-2-2B-mmproj-Q8_0.gguf | Q8_0 | 0.4 GB | 1.2 GB | ✅ Runs comfortably |
| Ternary-Bonsai-2-2B-PTQ1_0.gguf | Q1_0 | 0.4 GB | 1.3 GB | ✅ Runs comfortably |
| Ternary-Bonsai-2-2B-Q2_0.gguf | Q2_0 | 0.5 GB | 1.4 GB | ✅ Runs comfortably |
| Ternary-Bonsai-2-2B-mmproj-BF16.gguf | GGUF | 0.7 GB | 1.5 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Parameters
- 2.0 B
- Licence
- apache-2.0
- First seen on the Hub
- 2026-09-23
- Base model
- Qwen3.5-2B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-11-09
Compare with any image-text-to-text model