DeepSeek-V4-Flash-0731 vs Qwen3-Coder-480B-A35B-Instruct-FP8
Specs, VRAM requirements and download trends — updated 20 September 2026.
Qwen · B
Params
480.2 B
Context
262,144
30d
804 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-V4-Flash-0731 | Qwen3-Coder-480B-A35B-Instruct-FP8 |
|---|---|---|
| Parameters | 304.2 B | 480.2 B |
| Architecture | DeepseekV4ForCausalLM | Qwen3MoeForCausalLM |
| Context length | 1,048,576 | 262,144 |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 4,178,593 | 803,538 |
| Downloads all time | 7.0 M | 3.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-07-31 | 2025-07-22 |
Download trend
Daily snapshots, last 48 days (4 Aug – 20 Sep)
4.7 M236 K
DeepSeek-V4-Flash-0731
Qwen3-Coder-480B-A35B-Instruct-FP8
A overtook B on 5 Aug
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-Coder-480B-A35B-Instruct-FP8 · fp16 @ 256K ctx
2,835.7 GB / 24 GB
DeepSeek-V4-Flash-0731 · fp16 @ 1024K ctx
6,024.3 GB / 24 GB