Qwen3.8-27B-MLX-8bit vs Qwen2.5-VL-7B-Instruct-AWQ
Specs, VRAM requirements and download trends — updated 10 November 2026.
lmstudio-community · A · Open weights
Params
8.0 B
Context
—
30d
2.9 M
apache-2.0 · commercial OK
Qwen · B · Open weights
Params
8.3 B
Context
128,000
30d
1.3 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.8-27B-MLX-8bit | Qwen2.5-VL-7B-Instruct-AWQ |
|---|---|---|
| Parameters | 8.0 B | 8.3 B |
| Architecture | Qwen3_5ForConditionalGeneration | Qwen2_5_VLForConditionalGeneration |
| Context length | — | 128,000 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 1 |
| Downloads 30d | 2,893,827 | 1,324,897 |
| Downloads all time | 11.1 M | 15.8 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-08-14 | 2025-02-15 |
Download trend
Daily snapshots, last 80 days (23 Aug – 10 Nov)
4.8 M996 K
Qwen3.8-27B-MLX-8bit
Qwen2.5-VL-7B-Instruct-AWQ
A overtook B on 24 Aug
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-VL-7B-Instruct-AWQ · fp16 @ 125K ctx
27.5 GB / 24 GB
Qwen3.8-27B-MLX-8bit · fp16
34.2 GB / 24 GB