llama3.2:latest

llama · 3.2B · Q4_K_M

Good

Feb 28, 2026 · Apple M4 Pro

qwen3:0.6b

qwen3 · 751.63M · Q4_K_M

Good

Mar 2, 2026 · Apple M4

Global Score

73 vs 61

Hardware Fit

100 vs 100

Quality Score

61 vs 44

Hardware

llama3.2:latest qwen3:0.6b

MachineMac MiniMacBook Air

CPUApple M4 ProApple M4

Cores1410

RAM64 GB32 GB

GPUApple M4 ProApple M4

OSmacOS 15.7.4macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

llama3.2:latest qwen3:0.6b

Tokens/sec98.9144.3

TTFT125 ms81 ms

Load time2.3 s0.9 s

Memory usage22.1 GB4.1 GB

Memory %35%13%

HW Fit Score Breakdown

llama3.2:latest

Speed

40/40

TTFT

30/30

Memory

30/30

qwen3:0.6b

Speed

40/40

TTFT

30/30

Memory

30/30

Quality

llama3.2:latest

Reasoning

11/20

Coding

14/20

Instruction

12/20

Structured

12/15

Math

3/15

Multilingual

9/10

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

qwen3:0.6b

Reasoning

6/20

Coding

4/20

Instruction

10/20

Structured

13/15

Math

6/15

Multilingual

5/10

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

View llama3.2:latest details | View qwen3:0.6b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running