maternion/ling-3.0-tiny:8b

OLLAMA GGUF

bailingmoe3 · 7.9B · Q4_K_M

Excellent

Aug 25, 2026 · Apple M1 Pro

mistralai/magistral-small-2509

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

Global Score

88 vs 74

Hardware Fit

98 vs 66

Quality Score

83 vs 78

Hardware

maternion/ling-3.0… mistralai/magistra…

MachineMacBook ProMacBook Air

CPUApple M1 ProApple M4

Cores1010

RAM16 GB32 GB

GPUApple M1 ProApple M4

OSmacOS 26.6.2macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

maternion/ling-3.0… mistralai/magistra…

Tokens/sec73.07.9

First chunk175 ms1356 ms

TTFT175 ms1.4 s

Load time3.2 sN/A

Memory usage5.9 GB13.2 GB

Memory %37%41%

HW Fit Score Breakdown

maternion/ling-3.0-tiny…

Speed

50/50

TTFT

20/20

Memory

28/30

mistralai/magistral-sma…

Speed

16/50

TTFT

20/20

Memory

30/30

Quality

maternion/ling-3.0-tiny…

Reasoning

16/20

Coding

19/20

Instruction

15/20

Structured

15/15

Math

8/15

Multilingual

10/10

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

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

View maternion/ling-3.0… details | View mistralai/magistra… 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