Ternary-Bonsai-2-9B-gguf
A 9B-class vision-language model with ternary transformer weights, for llama.cpp (CUDA, Metal, CPU).
Params
9.0 B
Context
—
Downloads 30d
1.2 M
Likes
163
Download history
daily snapshots · 12 days1.2 M317 K
Oct 30Nov 3Nov 7Nov 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-2-9B-mmproj-BF16.gguf | GGUF | 0.9 GB | 2.9 GB | ✅ Runs comfortably |
| Ternary-Bonsai-2-9B-DFlash2-Q8_0.gguf | Q8_0 | 1.6 GB | 3.6 GB | ✅ Runs comfortably |
| Ternary-Bonsai-2-9B-PTQ1_0.gguf | Q1_0 | 2.0 GB | 4.0 GB | ✅ Runs comfortably |
| Ternary-Bonsai-2-9B-PQ2_0-MTP-Q8_0.gguf | Q2_0 | 2.7 GB | 4.8 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-11-10$0.08
input / 1M
$0.13
output / 1M
$0.04
cached input / 1M
$0.21
1M in + 1M out
- Context window
- 262,144 tokens
- Max output
- 65,536 tokens
- Providers
- 1
- Cheapest provider
- Darkbloom · $0.08 / $0.13
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- — / — / —
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✓ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Parameters
- 9.0 B
- Licence
- apache-2.0
- First seen on the Hub
- 2026-09-23
- Base model
- Qwen3.5-9B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-30
Compare with any image-text-to-text model
Popular comparisons
Appears in