Qwen2.5-3B-Instruct vs Bonsai-27B-mlx-1bit

Specs, VRAM requirements and download trends — updated 6 August 2026.

Qwen · A

Params

3.1 B

Context

32,768

30d

6.0 M

prism-ml · B

Params

1.7 B

Context

—

30d

457 K

apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Qwen2.5-3B-Instruct	Bonsai-27B-mlx-1bit
Parameters	3.1 B	1.7 B
Architecture	Qwen2ForCausalLM	Qwen3_5ForConditionalGeneration
Context length	32,768	—
Licence	other	apache-2.0
Commercial use	Unknown	Allowed
Languages	1	—
Downloads 30d	5,952,246	456,542
Downloads all time	110.0 M	457 K
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2024-09-17	2026-07-04

Daily snapshots, last 10 days (28 Jul – 6 Aug)

6.0 M204 K

Qwen2.5-3B-Instruct Bonsai-27B-mlx-1bit

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

Bonsai-27B-mlx-1bit · fp16 6.4 GB / 24 GB

✅ Runs comfortably

Qwen2.5-3B-Instruct · fp16 7.8 GB / 24 GB

✅ Runs comfortably