qwen3.5:4b

qwen35 · 4.7B · Q4_K_M

Excellent

Mar 2, 2026 · Apple M4

llama3:latest

llama · 8.0B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

80 vs 71

Hardware Fit

88 vs 95

Quality Score

76 vs 60

Hardware

qwen3.5:4b llama3:latest

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen3.5:4b llama3:latest

Tokens/sec16.622.3

TTFT369 ms295 ms

Load time1.5 s0.8 s

Memory usage6.5 GB5.6 GB

Memory %20%18%

HW Fit Score Breakdown

qwen3.5:4b

Speed

28/40

TTFT

30/30

Memory

30/30

llama3:latest

Speed

35/40

TTFT

30/30

Memory

30/30

Quality

qwen3.5:4b

Reasoning

16/20

Coding

14/20

Instruction

15/20

Structured

15/15

Math

7/15

Multilingual

9/10

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

llama3:latest

Reasoning

9/20

Coding

9/20

Instruction

15/20

Structured

13/15

Math

4/15

Multilingual

10/10

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

View qwen3.5:4b details | View llama3:latest details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running