qwen3:4b

qwen3 · 4.0B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

starling-lm:7b

llama · 7B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

47 vs 63

Hardware Fit

53 vs 97

Quality Score

45 vs 49

Hardware

qwen3:4b starling-lm:7b

Machine—MacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

qwen3:4b starling-lm:7b

Tokens/sec11.323.7

TTFT9.2 s234 ms

Load time0.1 s0.4 s

Memory usage7.2 GB5.3 GB

Memory %23%17%

HW Fit Score Breakdown

qwen3:4b

Speed

17/40

TTFT

6/30

Memory

30/30

starling-lm:7b

Speed

37/40

TTFT

30/30

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

starling-lm:7b

Reasoning

11/20

Coding

13/20

Instruction

6/20

Structured

3/15

Math

8/15

Multilingual

8/10

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

View qwen3:4b details | View starling-lm:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running