smollm2:135m

llama · 134.52M · F16

Marginal

Mar 1, 2026 · Apple M4

qwen3:1.7b

qwen3 · 2.0B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

Global Score

48 vs 70

Hardware Fit

100 vs 87

Quality Score

14 vs 59

Hardware

smollm2:135m qwen3:1.7b

MachineMacBook Air—

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

smollm2:135m qwen3:1.7b

Tokens/sec245.037.9

TTFT31 ms3.1 s

Load time0.4 s1.2 s

Memory usage0.6 GB4.9 GB

Memory %2%15%

HW Fit Score Breakdown

smollm2:135m

Speed

40/40

TTFT

30/30

Memory

30/30

qwen3:1.7b

Speed

40/40

TTFT

17/30

Memory

30/30

Quality

smollm2:135m

Reasoning

4/20

Coding

0/20

Instruction

6/20

Structured

2/15

Math

1/15

Multilingual

1/10

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

qwen3:1.7b

Reasoning

16/20

Coding

0/20

Instruction

13/20

Structured

14/15

Math

6/15

Multilingual

10/10

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

View smollm2:135m details | View qwen3:1.7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running