llama3.1:8b

llama · 8.0B · Q4_K_M

Not Rec.

Feb 28, 2026 · Apple M4 Pro

starcoder2:3b

starcoder2 · 3B · Q4_0

Marginal

Mar 2, 2026 · Apple M4

Global Score

64 vs 48

Hardware Fit

56 vs 100

Quality Score

70 vs 13

Hardware

llama3.1:8b 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

llama3.1:8b starcoder2:3b

Tokens/sec5.549.4

TTFT1.4 s155 ms

Load time3.7 s0.4 s

Memory usage28.6 GB3.0 GB

Memory %45%9%

HW Fit Score Breakdown

llama3.1:8b

Speed

5/40

TTFT

22/30

Memory

29/30

starcoder2:3b

Speed

40/40

TTFT

30/30

Memory

30/30

Quality

llama3.1:8b

Reasoning

12/20

Coding

17/20

Instruction

14/20

Structured

13/15

Math

4/15

Multilingual

10/10

Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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 llama3.1:8b details | View starcoder2:3b details

Run yours and compare

npx metrillm@latest bench

Requires Node 20+ and Ollama or LM Studio running