hf.co/unsloth/gpt-oss-20b-GGUF:Q4_K_M

OLLAMA GGUF

gpt-oss · 20.9B · unknown

Excellent

Aug 24, 2026 · Apple M1 Pro

mistralai/magistral-small-2509

LM-STUDIO MLX

mistral3 · 24B · 4bit

Good

Mar 4, 2026 · Apple M4

Global Score

86 vs 74

Hardware Fit

75 vs 66

Quality Score

90 vs 78

Hardware

hf.co/unsloth/gpt-… 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

hf.co/unsloth/gpt-… mistralai/magistra…

Tokens/sec35.97.9

First chunk1082 ms1356 ms

TTFT5.2 s1.4 s

Load time8.2 sN/A

Memory usage11.1 GB13.2 GB

Memory %69%41%

HW Fit Score Breakdown

hf.co/unsloth/gpt-oss-2…

Speed

50/50

TTFT

10/20

Memory

15/30

mistralai/magistral-sma…

Speed

16/50

TTFT

20/20

Memory

30/30

Quality

hf.co/unsloth/gpt-oss-2…

Reasoning

19/20

Coding

17/20

Instruction

15/20

Structured

14/15

Math

15/15

Multilingual

10/10

Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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 hf.co/unsloth/gpt-… 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