mistralai/magistral-small-2509

mistral3 · 24B · 4bit

Not Rec.

Mar 3, 2026 · Apple M4

google/gemma-3-12b

gemma3 · 12B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score

20 vs 77

Hardware Fit

65 vs 72

Quality Score

0 vs 79

Hardware

mistralai/magistra… google/gemma-3-12b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

mistralai/magistra… google/gemma-3-12b

Tokens/sec5.17.9

TTFT2.0 s1.8 s

Load time0.0 s0.0 s

Memory usage0.0 GB0.0 GB

Memory %0%0%

HW Fit Score Breakdown

mistralai/magistral-sma…

Speed

8/40

TTFT

27/30

Memory

30/30

google/gemma-3-12b

Speed

14/40

TTFT

28/30

Memory

30/30

Quality

mistralai/magistral-sma…

Reasoning

0/20

Coding

0/20

Instruction

0/20

Structured

0/15

Math

0/15

Multilingual

0/10

Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

google/gemma-3-12b

Reasoning

13/20

Coding

19/20

Instruction

14/20

Structured

15/15

Math

8/15

Multilingual

10/10

Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

View mistralai/magistra… details | View google/gemma-3-12b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running