mistralai/magistral-small-2509

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

hf.co/bloomer010/Ling-3.0-tiny-GGUF:Q8_0

OLLAMA GGUF

bailingmoe3 · 7.89B · unknown

Good

Aug 23, 2026 · Apple M1 Pro

Global Score

74 vs 68

Hardware Fit

66 vs 94

Quality Score

78 vs 57

Hardware

mistralai/magistra… hf.co/bloomer010/L…

MachineMacBook AirMacBook Pro

CPUApple M4Apple M1 Pro

Cores1010

RAM32 GB16 GB

GPUApple M4Apple M1 Pro

OSmacOS 26.3macOS 26.6.2

Archarm64arm64

Power Modebalancedbalanced

Performance

mistralai/magistra… hf.co/bloomer010/L…

Tokens/sec7.958.4

First chunk1356 ms220 ms

TTFT1.4 s220 ms

Load timeN/A0.0 s

Memory usage13.2 GB8.4 GB

Memory %41%53%

HW Fit Score Breakdown

mistralai/magistral-sma…

Speed

16/50

TTFT

20/20

Memory

30/30

hf.co/bloomer010/Ling-3…

Speed

50/50

TTFT

20/20

Memory

24/30

Quality

mistralai/magistral-sma…

Reasoning

14/20

Coding

18/20

Instruction

14/20

Structured

15/15

Math

7/15

Multilingual

10/10

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

hf.co/bloomer010/Ling-3…

Reasoning

19/20

Coding

17/20

Instruction

3/20

Structured

1/15

Math

15/15

Multilingual

2/10

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

View mistralai/magistra… details | View hf.co/bloomer010/L… 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