mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

qwen2.5:72b

OLLAMA GGUF

qwen2 · 72.7B · Q4_K_M

Not Rec.

Jun 27, 2026 · Cortex-X925

Global Score

73 vs 75

Hardware Fit

64 vs 50

Quality Score

77 vs 86

Hardware

mistralai/devstral… qwen2.5:72b

MachineMacBook ProNVIDIA NVIDIA_DGX_Spark

CPUApple M1 ProCortex-X925

Cores1020

RAM32 GB122 GB

GPUApple M1 ProDevice 2e12

OSmacOS 15.6.1Ubuntu 24.04.4 LTS

Archarm64arm64

Power Modebalancedperformance

Performance

mistralai/devstral… qwen2.5:72b

Tokens/sec11.94.4

First chunk7 ms529 ms

TTFT1.1 s529 ms

Load timeN/A49.7 s

Memory usage19.7 GB54.0 GB

Memory %62%44%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

qwen2.5:72b

Speed

4/50

TTFT

20/20

Memory

26/30

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

qwen2.5:72b

Reasoning

19/20

Coding

19/20

Instruction

12/20

Structured

14/15

Math

12/15

Multilingual

10/10

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

View mistralai/devstral… details | View qwen2.5:72b 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