Qwen3.6-35B-A3B-FP8 vs Qwen3.6-27B-GPTQ-Pro-4bit
Specs, VRAM requirements and download trends — updated 30 August 2026.
Qwen · A · Open weights
Params
36.0 B
Context
—
30d
4.0 M
apache-2.0 · commercial OK
groxaxo · B · Open weights
Params
27.4 B
Context
—
30d
909 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-FP8 | Qwen3.6-27B-GPTQ-Pro-4bit |
|---|---|---|
| Parameters | 36.0 B | 27.4 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | Qwen3_5ForConditionalGeneration |
| Context length | — | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 1 |
| Downloads 30d | 3,962,067 | 909,126 |
| Downloads all time | 49.4 M | 1.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-15 | 2026-04-22 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
13.5 M909 K
Qwen3.6-35B-A3B-FP8
Qwen3.6-27B-GPTQ-Pro-4bit
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.6-27B-GPTQ-Pro-4bit · fp16
25.2 GB / 24 GB
Qwen3.6-35B-A3B-FP8 · fp16
47.1 GB / 24 GB