mistralai/devstral-small-2-2512

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Oct 20, 2026 · Apple M1 Pro

lmstudio-community/meta-llama-3.1-8b-instruct

LM-STUDIO GGUF

llama · 8B · Q4_K_M

Good

Mar 5, 2026 · Apple M4 Pro

Global Score

73 vs 78

Hardware Fit

64 vs 100

Quality Score

77 vs 69

Hardware

mistralai/devstral… lmstudio-community…

MachineMacBook ProMac mini

CPUApple M1 ProApple M4 Pro

Cores1014

RAM32 GB64 GB

GPUApple M1 ProApple M4 Pro

OSmacOS 15.6.1macOS 15.7.4

Archarm64arm64

Power Modebalancedbalanced

Performance

mistralai/devstral… lmstudio-community…

Tokens/sec11.946.0

First chunk7 ms245 ms

TTFT1.1 s245 ms

Load timeN/AN/A

Memory usage19.7 GB4.6 GB

Memory %62%7%

HW Fit Score Breakdown

mistralai/devstral-smal…

Speed

25/50

TTFT

20/20

Memory

19/30

lmstudio-community/meta…

Speed

50/50

TTFT

20/20

Memory

30/30

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

lmstudio-community/meta…

Reasoning

11/20

Coding

15/20

Instruction

14/20

Structured

15/15

Math

4/15

Multilingual

10/10

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

View mistralai/devstral… details | View lmstudio-community… 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