Qwen3.6-35B-A3B-NVFP4 vs deepseek-v4-flash-0731-spark
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
0xSero · B · Open weights
Params
60.3 B
Context
1,048,576
30d
171 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-NVFP4 | deepseek-v4-flash-0731-spark |
|---|---|---|
| Parameters | 18.7 B | 60.3 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | DeepseekV4ForCausalLM |
| Context length | — | 1,048,576 |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 4,142,396 | 171,151 |
| Downloads all time | 39.6 M | 386 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-05-27 | 2026-08-01 |
Download trend
90 days of snapshots recorded — chart in 0 days.
39.6 M
Qwen3.6-35B-A3B-NVFP4 · all-time downloads
386 K
deepseek-v4-flash-0731-spark · all-time downloads
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.6-35B-A3B-NVFP4 · fp16
29.1 GB / 24 GB
deepseek-v4-flash-0731-spark · fp16 @ 1024K ctx
1,276.0 GB / 24 GB