Mistral Large 2 vs Gemma 3 27B
Architecture Comparison
SpecMistral Large 2Gemma 3 27B
TypeDENSEDENSE
Total Parameters123B27B
Active Parameters123B27B
Layers8862
Hidden Dimension12,2883,584
Attention Heads9632
KV Heads816
Context Length131,072131,072
Precision (default)BF16BF16
Memory Requirements
PrecisionMistral Large 2Gemma 3 27B
BF16 Weights246.0 GB54.0 GB
FP8 Weights123.0 GB27.0 GB
INT4 Weights61.5 GB13.5 GB
KV-Cache / Token360448 B507904 B
Activation Estimate3.50 GB1.50 GB
Minimum GPUs Needed (BF16)
H100 SXM4 GPUs1 GPU
L40S7 GPUs2 GPUs
Quality Benchmarks
BenchmarkMistral Large 2Gemma 3 27B
Overall8276
MMLU84.078.0
HumanEval53.048.0
GSM8K91.285.0
MT-Bench84.082.0
Mistral Large 2
MMLU
84.0
HumanEval
53.0
GSM8K
91.2
MT-Bench
84.0
Gemma 3 27B
MMLU
78.0
HumanEval
48.0
GSM8K
85.0
MT-Bench
82.0
Capabilities
FeatureMistral Large 2Gemma 3 27B
Tool Use✓ Yes✓ Yes
Vision✗ No✓ Yes
Code✓ Yes✓ Yes
Math✓ Yes✓ Yes
Reasoning✗ No✗ No
Multilingual✓ Yes✓ Yes
Structured Output✓ Yes✓ Yes
API Pricing Comparison
Cheapest Output (Mistral Large 2)
$2.50/M
Input: $2.50/M
Cheapest Output (Gemma 3 27B)
$0.20/M
Input: $0.10/M
| Provider | Mistral Large 2 In $/M | Out $/M | Gemma 3 27B In $/M | Out $/M |
|---|---|---|---|---|
| — | — | $0.10 | $0.20 | |
| together | $2.50 | $2.50 | $0.30 | $0.30 |
| mistral | $2.00 | $6.00 | — | — |
Recommendation Summary
- ‣Mistral Large 2 scores higher on overall quality (82 vs 76).
- ‣Gemma 3 27B is cheaper per output token ($0.20/M vs $2.50/M).
- ‣Gemma 3 27B has a smaller memory footprint (54.0 GB vs 246.0 GB BF16), making it easier to deploy on fewer GPUs.
- ‣Mistral Large 2 is stronger at code generation (HumanEval: 53.0 vs 48.0).
- ‣Mistral Large 2 is better at math reasoning (GSM8K: 91.2 vs 85.0).