llama3.2:3b

llama · 3.2B · Q4_K_M

Good

Mar 1, 2026 · Apple M4

neural-chat:7b

llama · 7B · Q4_0

Good

Mar 2, 2026 · Apple M4

Global Score

69 vs 71

Hardware Fit

98 vs 96

Quality Score

49 vs 55

Hardware

llama3.2:3b neural-chat:7b

MachineMacBook AirMacBook Air

CPUApple M4Apple M4

Cores1010

RAM32 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modeunknownbalanced

Performance

llama3.2:3b neural-chat:7b

Tokens/sec27.822.5

TTFT285 ms242 ms

Load time1.9 s0.4 s

Memory usage7.0 GB4.5 GB

Memory %22%14%

HW Fit Score Breakdown

llama3.2:3b

Speed

38/40

TTFT

30/30

Memory

30/30

neural-chat:7b

Speed

36/40

TTFT

30/30

Memory

30/30

Quality

llama3.2:3b

Reasoning

11/20

Coding

0/20

Instruction

14/20

Structured

12/15

Math

3/15

Multilingual

9/10

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

neural-chat:7b

Reasoning

7/20

Coding

9/20

Instruction

12/20

Structured

12/15

Math

7/15

Multilingual

8/10

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

View llama3.2:3b details | View neural-chat:7b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running