Ternary-Bonsai-27B-mlx-2bit vs Qwen2.5-Math-1.5B

Specs, VRAM requirements and download trends — updated 4 September 2026.

prism-ml · A
Params
2.6 B
Context
30d
1.1 M
apache-2.0 · commercial OK
Qwen · B
Params
1.5 B
Context
4,096
30d
208 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Ternary-Bonsai-27B-mlx-2bit Qwen2.5-Math-1.5B
Parameters 2.6 B 1.5 B
Architecture Qwen3_5ForConditionalGeneration Qwen2ForCausalLM
Context length 4,096
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages 1
Downloads 30d 1,065,043 207,749
Downloads all time 2.9 M 7.2 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-07-04 2024-09-16

Download trend

Daily snapshots, last 50 days (3 Aug – 21 Sep)

2.1 M197 K
Ternary-Bonsai-27B-mlx-2bit Qwen2.5-Math-1.5B

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

Qwen2.5-Math-1.5B · fp16 4.1 GB / 24 GB
✅ Runs comfortably
Ternary-Bonsai-27B-mlx-2bit · fp16 10.2 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons