GreenBitAI/Ternary-Bonsai-2-27B-gbx
just landed · new, unvettedmodel
New, unvetted: created or first seen in the last few days, not from a trusted org and not past the signal threshold yet.
Bonsai 2 ships without a draft model; this head starts from the multi-token prediction head of Qwen3.8-27B, which Bonsai 2 is built from, and is distilled on text generated by Bonsai 2 itself -- prose, code, chat and coding-agent sessions. Dense, 27B params. Context: 256K tokens (config). License: apache-2.0.
- Org
- GreenBitAI
- Released
- 2026-10-20
- Status
- just landed · new, unvetted
- License
- apache-2.0 (permissive)
- Parameters
- 27.4B
- Architecture
- dense
- Context
- 262,144 tokens
- Task
- image-text-to-text · vision
- Signal
- 2 HF likes · 102 downloads
Runs on
estimate from params; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~19.5 GB (estimated size): 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~32.2 GB (estimated size): 48GB GPU (RTX 6000 Ada / A6000), Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~57.8 GB (estimated size): 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)
Links
First published here 2026-10-20 · updated 2026-10-22 · markdown · JSON