qwen3:8b

qwen3 · 8.2B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

mistral-nemo:12b

llama · 12.2B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score

42 vs 73

Hardware Fit

60 vs 86

Quality Score

30 vs 65

Hardware

qwen3:8b mistral-nemo:12b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

qwen3:8b mistral-nemo:12b

Tokens/sec18.214.6

TTFT12.4 s371 ms

Load time2.7 s1.0 s

Memory usage9.5 GB13.3 GB

Memory %30%42%

HW Fit Score Breakdown

qwen3:8b

Speed

27/40

TTFT

3/30

Memory

30/30

mistral-nemo:12b

Speed

26/40

TTFT

30/30

Memory

30/30

Quality

qwen3:8b

Reasoning

9/20

Coding

0/20

Instruction

5/20

Structured

4/15

Math

3/15

Multilingual

9/10

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

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

View qwen3:8b details | View mistral-nemo:12b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running