DeepSeek-R1 vs Qwen3-235B-A22B-FP8

Specs, VRAM requirements and download trends — updated 6 August 2026.

deepseek-ai · A
Params
684.5 B
Context
163,840
30d
9.9 M
mit · commercial OK
Qwen · B
Params
235.1 B
Context
40,960
30d
163 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification DeepSeek-R1 Qwen3-235B-A22B-FP8
Parameters 684.5 B 235.1 B
Architecture DeepseekV3ForCausalLM Qwen3MoeForCausalLM
Context length 163,840 40,960
Licence mit apache-2.0
Commercial use Allowed Allowed
Languages
Downloads 30d 9,934,359 163,422
Downloads all time 46.8 M 1.0 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-01-20 2025-04-28

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

9.9 M163 K
DeepSeek-R1 Qwen3-235B-A22B-FP8

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

Qwen3-235B-A22B-FP8 · fp16 298.7 GB / 24 GB
❌ Won’t fit
DeepSeek-R1 · fp16 @ 160K ctx 2,811.5 GB / 24 GB
❌ Won’t fit

Adjacent comparisons