CanItRun Logocanitrun.

DeepSeek V3 671B vs Qwen3 235B-A22B (MoE)

Side-by-side VRAM requirements, benchmark scores, and GPU compatibility for local AI inference.

Quick verdict

Qwen3 235B-A22B (MoE) is more hardware-efficient — it needs 149.9 GB at Q4_K_M vs 423.7 GB for DeepSeek V3 671B, fitting on 20 GPUs natively.

VRAM at each quantization (8k context)

QuantDeepSeek V3 671BQwen3 235B-A22B (MoE)Diff
FP323006.7 GB1054.6 GB+185%
BF161503.6 GB528.2 GB+185%
FP161503.6 GB528.2 GB+185%
Q8_0752.1 GB265.0 GB+184%
Q6_K616.8 GB217.6 GB+183%
Q5_K_M484.6 GB171.3 GB+183%
Q4_K_M423.7 GB149.9 GB+183%
Q3_K_M323.7 GB114.9 GB+182%
Q2_K247.8 GB88.4 GB+180%
NVFP4376.3 GB133.4 GB+182%

Diff is DeepSeek V3 671B relative to Qwen3 235B-A22B (MoE). Green = lower VRAM (fits more GPUs).

Model specifications

SpecDeepSeek V3 671BQwen3 235B-A22B (MoE)
OrgDeepSeekAlibaba
Parameters671B235B
ArchitectureMoE (37B active)MoE (22B active)
Context125k tokens128k tokens
Modalitiestexttext
LicenseMITApache 2.0
CommercialYesYes
Released2024-12-272025-04-29
GPUs (native)4 / 10720 / 107

Benchmark scores

BenchmarkDeepSeek V3 671BQwen3 235B-A22B (MoE)
MMLU-Pro75.984.4
GPQA Diamond59.1—
IFEval86.1—
MATH90.2—
LiveCodeBench40.5—

Green = higher score (better). — = not yet available.

GPUs that run only DeepSeek V3 671B(0)

Every GPU that runs DeepSeek V3 671B also runs Qwen3 235B-A22B (MoE).

GPUs that run only Qwen3 235B-A22B (MoE)(16)

GPUs that run both natively(4)

Which should you use?

Choose DeepSeek V3 671B if:
  • • You want maximum capability and have a 424 GB+ GPU
Choose Qwen3 235B-A22B (MoE) if:
  • • You have limited VRAM — it's a smaller model needing 149.9 GB vs 423.7 GB
  • • Long context matters — it supports 128k tokens vs 125k
  • • Benchmark quality matters — scores 84.4 vs 75.9 on MMLU-Pro
  • • You need chain-of-thought reasoning

Frequently asked questions

Which is better, DeepSeek V3 671B or Qwen3 235B-A22B (MoE)?
DeepSeek V3 671B has 671B parameters vs 235B for Qwen3 235B-A22B (MoE), so DeepSeek V3 671B is the larger model. Qwen3 235B-A22B (MoE) is more hardware-efficient, needing 149.9 GB at Q4_K_M vs 423.7 GB. Qwen3 235B-A22B (MoE) runs on more GPUs natively (20 vs 4). On MMLU-Pro, Qwen3 235B-A22B (MoE) scores higher (84.4 vs 75.9).
How much VRAM does DeepSeek V3 671B need vs Qwen3 235B-A22B (MoE)?
At Q4_K_M quantization with 8k context, DeepSeek V3 671B needs approximately 423.7 GB of VRAM, while Qwen3 235B-A22B (MoE) needs 149.9 GB. At FP16, DeepSeek V3 671B requires 1503.6 GB vs 528.2 GB for Qwen3 235B-A22B (MoE).
Can you run DeepSeek V3 671B on the same GPUs as Qwen3 235B-A22B (MoE)?
Yes, 4 GPUs can run both natively in VRAM, including Apple M4 Ultra (384GB), Apple M3 Ultra (512GB), Apple M3 Ultra (256GB). However, no GPU can run DeepSeek V3 671B without also fitting Qwen3 235B-A22B (MoE), and 16 GPUs can run Qwen3 235B-A22B (MoE) but not DeepSeek V3 671B.
What is the difference between DeepSeek V3 671B and Qwen3 235B-A22B (MoE)?
DeepSeek V3 671B has 671B parameters (37B active, MoE) with a 125k context window. Qwen3 235B-A22B (MoE) has 235B parameters (22B active, MoE) with a 128k context window. Licensing differs: DeepSeek V3 671B is MIT while Qwen3 235B-A22B (MoE) is Apache 2.0.
Which model fits in 24 GB of VRAM, DeepSeek V3 671B or Qwen3 235B-A22B (MoE)?
Neither fits in 24 GB at Q4_K_M — DeepSeek V3 671B needs 423.7 GB and Qwen3 235B-A22B (MoE) needs 149.9 GB. Both require at least a 48 GB GPU.
Full DeepSeek V3 671B page →Full Qwen3 235B-A22B (MoE) page →Check your hardware →