Qwen 2.5 72B vs DeepSeek V3
Architecture Comparison
SpecQwen 2.5 72BDeepSeek V3
TypeDENSEMOE
Total Parameters72.7B671B
Active Parameters72.7B37B
Layers8061
Hidden Dimension8,1927,168
Attention Heads64128
KV Heads81
Context Length131,072131,072
Precision (default)BF16BF16
Total ExpertsN/A256
Active ExpertsN/A8
Memory Requirements
PrecisionQwen 2.5 72BDeepSeek V3
BF16 Weights145.4 GB1342.0 GB
FP8 Weights72.7 GB671.0 GB
INT4 Weights36.4 GB335.5 GB
KV-Cache / Token327680 B31232 B
Activation Estimate2.50 GB3.00 GB
Minimum GPUs Needed (BF16)
H100 SXM3 GPUsN/A
L40S4 GPUsN/A
Quality Benchmarks
BenchmarkQwen 2.5 72BDeepSeek V3
Overall8486
MMLU85.387.1
HumanEval56.065.0
GSM8K91.689.3
MT-Bench86.087.0
Qwen 2.5 72B
MMLU
85.3
HumanEval
56.0
GSM8K
91.6
MT-Bench
86.0
DeepSeek V3
MMLU
87.1
HumanEval
65.0
GSM8K
89.3
MT-Bench
87.0
Capabilities
FeatureQwen 2.5 72BDeepSeek V3
Tool Use✓ Yes✓ Yes
Vision✗ No✗ No
Code✓ Yes✓ Yes
Math✓ Yes✓ Yes
Reasoning✗ No✗ No
Multilingual✓ Yes✓ Yes
Structured Output✓ Yes✓ Yes
API Pricing Comparison
Cheapest Output (Qwen 2.5 72B)
$0.90/M
Input: $0.90/M
Cheapest Output (DeepSeek V3)
$0.42/M
Input: $0.28/M
| Provider | Qwen 2.5 72B In $/M | Out $/M | DeepSeek V3 In $/M | Out $/M |
|---|---|---|---|---|
| deepseek | — | — | $0.28 | $0.42 |
| together | $0.90 | $0.90 | $0.50 | $2.80 |
| fireworks | $0.90 | $0.90 | — | — |
Recommendation Summary
- ‣DeepSeek V3 scores higher on overall quality (86 vs 84).
- ‣DeepSeek V3 is cheaper per output token ($0.42/M vs $0.90/M).
- ‣Qwen 2.5 72B has a smaller memory footprint (145.4 GB vs 1342.0 GB BF16), making it easier to deploy on fewer GPUs.
- ‣Qwen 2.5 72B uses DENSE architecture while DeepSeek V3 uses MOE. MoE models activate fewer parameters per token, improving inference efficiency.
- ‣DeepSeek V3 is stronger at code generation (HumanEval: 65.0 vs 56.0).
- ‣Qwen 2.5 72B is better at math reasoning (GSM8K: 91.6 vs 89.3).