qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

codellama:7b

OLLAMA GGUF

llama · 7B · Q4_0

Good

Mar 1, 2026 · Apple M4

Global Score

53 vs 63

Hardware Fit

82 vs 97

Quality Score

41 vs 49

Hardware

qwen3.5:4b-mlx codellama:7b

MachineMac miniMacBook Air

CPUApple M2Apple M4

Cores810

RAM8 GB32 GB

GPUApple M2Apple M4

OSmacOS 26.5.2macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx codellama:7b

Tokens/sec24.723.6

First chunk302 msN/A

TTFT7.4 s297 ms

Load time3.2 s0.9 s

Memory usage3.8 GB12.6 GB

Memory %47%39%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed

50/50

TTFT

6/20

Memory

26/30

codellama:7b

Speed

37/50

TTFT

30/20

Memory

30/30

Quality

qwen3.5:4b-mlx

Reasoning

13/20

Coding

2/20

Instruction

4/20

Structured

4/15

Math

10/15

Multilingual

8/10

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

codellama:7b

Reasoning

6/20

Coding

7/20

Instruction

12/20

Structured

13/15

Math

3/15

Multilingual

8/10

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

View qwen3.5:4b-mlx details | View codellama:7b 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