qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

gemma3:4b

OLLAMA GGUF

gemma3 · 4.3B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

Global Score

53 vs 76

Hardware Fit

82 vs 92

Quality Score

41 vs 69

Hardware

qwen3.5:4b-mlx gemma3:4b

MachineMac miniNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super

CPUApple M2Cortex-A78AE

Cores86

RAM8 GB7 GB

GPUApple M2Integrated / Unknown

OSmacOS 26.5.2Ubuntu 22.04.5 LTS

Archarm64arm64

Power Modebalancedbalanced

Performance

qwen3.5:4b-mlx gemma3:4b

Tokens/sec24.715.0

First chunk302 ms2380 ms

TTFT7.4 s2.4 s

Load time3.2 s13.6 s

Memory usage3.8 GB2.6 GB

Memory %47%35%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed

50/50

TTFT

6/20

Memory

26/30

gemma3:4b

Speed

45/50

TTFT

18/20

Memory

29/30

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

gemma3:4b

Reasoning

11/20

Coding

17/20

Instruction

13/20

Structured

14/15

Math

4/15

Multilingual

10/10

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

View qwen3.5:4b-mlx details | View gemma3:4b 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