Qwen3.6-35B-A3B-NVFP4 vs Qwen2.5-Coder-14B-Instruct-GGUF
Specs, VRAM requirements and download trends — updated 25 October 2026.
nvidia · A · Open weights
Params
18.7 B
Context
—
30d
4.1 M
apache-2.0 · commercial OK
Qwen · B · Open weights
Params
14.0 B
Context
32,768
30d
172 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-NVFP4 | Qwen2.5-Coder-14B-Instruct-GGUF |
|---|---|---|
| Parameters | 18.7 B | 14.0 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | — |
| Context length | — | 32,768 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 1 |
| Downloads 30d | 4,142,396 | 172,244 |
| Downloads all time | 39.6 M | 1.2 M |
| Quantizations on the Hub | SAFETENSORS | GGUF |
| Gated | No | No |
| First seen on the Hub | 2026-05-27 | 2024-11-09 |
Download trend
90 days of snapshots recorded — chart in 0 days.
39.6 M
Qwen3.6-35B-A3B-NVFP4 · all-time downloads
1.2 M
Qwen2.5-Coder-14B-Instruct-GGUF · all-time downloads
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-Coder-14B-Instruct-GGUF · Q4_0
12.0 GB / 24 GB
Qwen3.6-35B-A3B-NVFP4 · fp16
29.1 GB / 24 GB