mistral:latest

llama · 7.2B · Q4_0

Good

Feb 28, 2026 · Apple M4 Pro

starcoder2:3b

starcoder2 · 3B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

Global Score

76 vs 48

Hardware Fit

100 vs 100

Quality Score

60 vs 13

Hardware

mistral:latest starcoder2:3b

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

mistral:latest starcoder2:3b

Tokens/sec54.349.4

TTFT124 ms155 ms

Load time0.0 s0.4 s

Memory usage9.9 GB3.0 GB

Memory %15%9%

HW Fit Score Breakdown

mistral:latest

Speed

40/40

TTFT

30/30

Memory

30/30

starcoder2:3b

Speed

40/40

TTFT

30/30

Memory

30/30

Quality

mistral:latest

Reasoning

8/20

Coding

15/20

Instruction

13/20

Structured

12/15

Math

3/15

Multilingual

9/10

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

starcoder2:3b

Reasoning

0/20

Coding

2/20

Instruction

5/20

Structured

2/15

Math

2/15

Multilingual

2/10

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

View mistral:latest details | View starcoder2:3b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running