Qwen3.6-35B-A3B-NVFP4 vs deepseek-coder-6.7B-instruct-AWQ
Specs, VRAM requirements and download trends — updated 7 August 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-NVFP4 | deepseek-coder-6.7B-instruct-AWQ |
|---|---|---|
| Parameters | 18.7 B | 6.7 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | LlamaForCausalLM |
| Context length | — | 16,384 |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | — | — |
| Downloads 30d | 8,020,372 | 159,257 |
| Downloads all time | 34.6 M | 1.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-05-27 | 2023-11-05 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
12.6 M159 K
Qwen3.6-35B-A3B-NVFP4
deepseek-coder-6.7B-instruct-AWQ
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
deepseek-coder-6.7B-instruct-AWQ · fp16
5.8 GB / 24 GB
Qwen3.6-35B-A3B-NVFP4 · fp16
29.1 GB / 24 GB