qwen3:4b

qwen3 · 4.0B · Q4_K_M

Marginal

Mar 1, 2026 · Apple M4

yi:6b

llama · 6B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score

47 vs 77

Hardware Fit

53 vs 100

Quality Score

45 vs 67

Hardware

qwen3:4b yi:6b

Machine—MacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

qwen3:4b yi:6b

Tokens/sec11.327.6

TTFT9.2 s210 ms

Load time0.1 s0.4 s

Memory usage7.2 GB3.6 GB

Memory %23%11%

HW Fit Score Breakdown

qwen3:4b

Speed

17/40

TTFT

6/30

Memory

30/30

yi:6b

Speed

40/40

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

yi:6b

Reasoning

11/20

Coding

12/20

Instruction

13/20

Structured

12/15

Math

13/15

Multilingual

6/10

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

View qwen3:4b details | View yi:6b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running