llama3.2:3b

llama · 3.2B · Q4_K_M

Good

Mar 2, 2026 · Apple M4

wizardlm2:7b

llama · 7B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

78 vs 65

Hardware Fit

100 vs 97

Quality Score

63 vs 43

Hardware

llama3.2:3b wizardlm2:7b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

llama3.2:3b wizardlm2:7b

Tokens/sec44.123.2

TTFT178 ms264 ms

Load time0.8 s0.6 s

Memory usage7.0 GB9.9 GB

Memory %22%31%

HW Fit Score Breakdown

llama3.2:3b

Speed

40/40

TTFT

30/30

Memory

30/30

wizardlm2:7b

Speed

37/40

TTFT

30/30

Memory

30/30

Quality

llama3.2:3b

Reasoning

11/20

Coding

14/20

Instruction

14/20

Structured

12/15

Math

3/15

Multilingual

9/10

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

wizardlm2:7b

Reasoning

6/20

Coding

11/20

Instruction

10/20

Structured

4/15

Math

4/15

Multilingual

8/10

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

View llama3.2:3b details | View wizardlm2:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running