Skip to content

Mistral Small 24B vs Gemma 3 27B

Mistral
Mistral Small 24B

Mistral AI · 24B params · Quality: 68

Google
Gemma 3 27B

Google · 27B params · Quality: 76

Architecture Comparison

SpecMistral Small 24BGemma 3 27B
TypeDENSEDENSE
Total Parameters24B27B
Active Parameters24B27B
Layers4062
Hidden Dimension6,1443,584
Attention Heads4832
KV Heads816
Context Length32,768131,072
Precision (default)BF16BF16

Memory Requirements

PrecisionMistral Small 24BGemma 3 27B
BF16 Weights48.0 GB54.0 GB
FP8 Weights24.0 GB27.0 GB
INT4 Weights12.0 GB13.5 GB
KV-Cache / Token163840 B507904 B
Activation Estimate1.50 GB1.50 GB

Minimum GPUs Needed (BF16)

H100 SXM1 GPU1 GPU
L40S2 GPUs2 GPUs

Quality Benchmarks

BenchmarkMistral Small 24BGemma 3 27B
Overall6876
MMLU72.078.0
HumanEval45.048.0
GSM8K70.085.0
MT-Bench77.082.0

Mistral Small 24B

MMLU
72.0
HumanEval
45.0
GSM8K
70.0
MT-Bench
77.0

Gemma 3 27B

MMLU
78.0
HumanEval
48.0
GSM8K
85.0
MT-Bench
82.0

Capabilities

FeatureMistral Small 24BGemma 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 Small 24B)

$0.30/M

Input: $0.10/M

Cheapest Output (Gemma 3 27B)

$0.20/M

Input: $0.10/M

ProviderMistral Small 24B In $/MOut $/MGemma 3 27B In $/MOut $/M
google$0.10$0.20
mistral$0.10$0.30
together$0.30$0.30$0.30$0.30

Recommendation Summary

  • Gemma 3 27B scores higher on overall quality (76 vs 68).
  • Gemma 3 27B is cheaper per output token ($0.20/M vs $0.30/M).
  • Mistral Small 24B has a smaller memory footprint (48.0 GB vs 54.0 GB BF16), making it easier to deploy on fewer GPUs.
  • Gemma 3 27B supports a longer context window (131,072 vs 32,768 tokens).
  • Gemma 3 27B is stronger at code generation (HumanEval: 48.0 vs 45.0).
  • Gemma 3 27B is better at math reasoning (GSM8K: 85.0 vs 70.0).

Compare Other Models