mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

qwen2.5-coder-1.5b-instruct-mlx

LM-STUDIO MLX

qwen2 · 1.5B · 8bit

Good

Mar 4, 2026 · Apple M4

Global Score

69 vs 70

Hardware Fit

50 vs 100

Quality Score

77 vs 57

Hardware

mistralai/devstral… qwen2.5-coder-1.5b…

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

mistralai/devstral… qwen2.5-coder-1.5b…

Tokens/sec5.758.4

First chunk5007 ms234 ms

TTFT5.0 s234 ms

Load timeN/AN/A

Memory usage13.2 GB1.5 GB

Memory %41%5%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

11/50

TTFT

9/20

Memory

30/30

qwen2.5-coder-1.5b-inst…

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

mistralai/devstral-smal…

Reasoning

16/20

Coding

18/20

Instruction

13/20

Structured

14/15

Math

6/15

Multilingual

10/10

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

qwen2.5-coder-1.5b-inst…

Reasoning

9/20

Coding

12/20

Instruction

13/20

Structured

12/15

Math

4/15

Multilingual

7/10

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

View mistralai/devstral… details | View qwen2.5-coder-1.5b… 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