mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

gemma3:4b

OLLAMA GGUF

gemma3 · 4.3B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

Global Score

73 vs 76

Hardware Fit

64 vs 92

Quality Score

77 vs 69

Hardware

mistralai/devstral… gemma3:4b

MachineMacBook ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super

CPUApple M1 ProCortex-A78AE

Cores106

RAM32 GB7 GB

GPUApple M1 ProIntegrated / Unknown

OSmacOS 15.6.1Ubuntu 22.04.5 LTS

Archarm64arm64

Power Modebalancedbalanced

Performance

mistralai/devstral… gemma3:4b

Tokens/sec11.915.0

First chunk7 ms2380 ms

TTFT1.1 s2.4 s

Load timeN/A13.6 s

Memory usage19.7 GB2.6 GB

Memory %62%35%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

gemma3:4b

Speed

45/50

TTFT

18/20

Memory

29/30

Quality

mistralai/devstral-smal…

Reasoning

17/20

Coding

16/20

Instruction

13/20

Structured

14/15

Math

7/15

Multilingual

10/10

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

gemma3:4b

Reasoning

11/20

Coding

17/20

Instruction

13/20

Structured

14/15

Math

4/15

Multilingual

10/10

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

View mistralai/devstral… details | View gemma3:4b details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest