starcoder2:7b

OLLAMA GGUF

starcoder2 · 7B · Q4_0

Not Rec.

Mar 2, 2026 · Apple M4

qwen3.5:27b

OLLAMA GGUF

qwen35 · 27.8B · Q4_K_M

Good

Mar 10, 2026 · Apple M4

Global Score

35 vs 66

Hardware Fit

97 vs 34

Quality Score

8 vs 80

Hardware

starcoder2:7b qwen3.5:27b

MachineMacBook AirMac mini

CPUApple M4Apple M4

Cores1010

RAM32 GB24 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

starcoder2:7b qwen3.5:27b

Tokens/sec23.84.0

First chunkN/A1655 ms

TTFT251 ms1.7 s

Load time0.4 s12.9 s

Memory usage6.3 GB21.3 GB

Memory %20%89%

HW Fit Score Breakdown

starcoder2:7b

Speed

37/50

TTFT

30/20

Memory

30/30

qwen3.5:27b

Speed

8/50

TTFT

20/20

Memory

6/30

Quality

starcoder2:7b

Reasoning

0/20

Coding

1/20

Instruction

4/20

Structured

2/15

Math

0/15

Multilingual

1/10

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

qwen3.5:27b

Reasoning

16/20

Coding

18/20

Instruction

9/20

Structured

15/15

Math

12/15

Multilingual

10/10

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

View starcoder2:7b details | View qwen3.5:27b details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest