qwen3:4b

qwen3 · 4.0B · Q4_K_M

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

53 vs 87

Quality Score

45 vs 59

Hardware

qwen3:4b qwen3:1.7b

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

qwen3:4b qwen3:1.7b

Tokens/sec11.337.9

TTFT9.2 s3.1 s

Load time0.1 s1.2 s

Memory usage7.2 GB4.9 GB

Memory %23%15%

HW Fit Score Breakdown

qwen3:4b

Speed

17/40

TTFT

6/30

Memory

30/30

qwen3:1.7b

Speed

40/40

TTFT

17/30

Memory

30/30

Quality

qwen3:4b

Reasoning

4/20

Coding

6/20

Instruction

8/20

Structured

6/15

Math

12/15

Multilingual

9/10

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

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 qwen3:4b details | View qwen3:1.7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running