qwen3:0.6b

qwen3 · 751.63M · Q4_K_M

Good

Mar 2, 2026 · Apple M4

mistralai/magistral-small-2509

mistral3 · 24B · 4bit

Not Rec.

Mar 3, 2026 · Apple M4

Global Score

61 vs 20

Hardware Fit

100 vs 65

Quality Score

44 vs 0

Hardware

qwen3:0.6b mistralai/magistra…

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen3:0.6b mistralai/magistra…

Tokens/sec144.35.1

TTFT81 ms2.0 s

Load time0.9 s0.0 s

Memory usage4.1 GB0.0 GB

Memory %13%0%

HW Fit Score Breakdown

qwen3:0.6b

Speed

40/40

TTFT

30/30

Memory

30/30

mistralai/magistral-sma…

Speed

8/40

TTFT

27/30

Memory

30/30

Quality

qwen3:0.6b

Reasoning

6/20

Coding

4/20

Instruction

10/20

Structured

13/15

Math

6/15

Multilingual

5/10

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

mistralai/magistral-sma…

Reasoning

0/20

Coding

0/20

Instruction

0/20

Structured

0/15

Math

0/15

Multilingual

0/10

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

View qwen3:0.6b details | View mistralai/magistra… details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running