mistral-nemo:12b

llama · 12.2B · Q4_0

Good

Mar 1, 2026 · Apple M4

qwen3.5:0.8b

qwen35 · 873.44M · Q8_0

Good

Mar 2, 2026 · Apple M4

Global Score

73 vs 70

Hardware Fit

86 vs 99

Quality Score

65 vs 51

Hardware

mistral-nemo:12b qwen3.5:0.8b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

mistral-nemo:12b qwen3.5:0.8b

Tokens/sec14.648.2

TTFT371 ms195 ms

Load time1.0 s1.0 s

Memory usage13.3 GB2.5 GB

Memory %42%8%

HW Fit Score Breakdown

mistral-nemo:12b

Speed

26/40

TTFT

30/30

Memory

30/30

qwen3.5:0.8b

Speed

40/40

TTFT

30/30

Memory

29/30

Quality

mistral-nemo:12b

Reasoning

12/20

Coding

13/20

Instruction

11/20

Structured

15/15

Math

4/15

Multilingual

10/10

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

qwen3.5:0.8b

Reasoning

9/20

Coding

6/20

Instruction

11/20

Structured

13/15

Math

5/15

Multilingual

7/10

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

View mistral-nemo:12b details | View qwen3.5:0.8b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running