Qwen2.5-3B-Instruct vs Ternary-Bonsai-27B-mlx-2bit
Specs, VRAM requirements and download trends — updated 10 November 2026.
prism-ml · B · Open weights
Params
2.6 B
Context
—
30d
1.0 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-3B-Instruct | Ternary-Bonsai-27B-mlx-2bit |
|---|---|---|
| Parameters | 3.1 B | 2.6 B |
| Architecture | Qwen2ForCausalLM | Qwen3_5ForConditionalGeneration |
| Context length | 32,768 | — |
| Licence | other | apache-2.0 |
| Commercial use | Unknown | Allowed |
| Languages | 1 | — |
| Downloads 30d | 2,587,484 | 1,012,597 |
| Downloads all time | 125.6 M | 4.7 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-09-17 | 2026-07-04 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
7.6 M962 K
Qwen2.5-3B-Instruct
Ternary-Bonsai-27B-mlx-2bit
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-3B-Instruct · fp16
7.8 GB / 24 GB
Ternary-Bonsai-27B-mlx-2bit · fp16
10.2 GB / 24 GB