qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 8bit

Good

Mar 3, 2026 · Apple M4

gemma4:e4b

OLLAMA GGUF

gemma4 · 8.0B · Q4_K_M

Excellent

Apr 3, 2026 · AMD RYZEN AI MAX+ 395

Global Score

70 vs 84

Hardware Fit

93 vs 98

Quality Score

60 vs 78

Hardware

qwen3.5-2b-mlx gemma4:e4b

MachineMacBook AirAZW GTR Pro

CPUApple M4AMD RYZEN AI MAX+ 395

Cores1032

RAM32 GB125 GB

GPUApple M4Radeon 8060S

OSmacOS 26.3Ubuntu 24.04.4 LTS

Archarm64x64

Power Modebalancedperformance

Performance

qwen3.5-2b-mlx gemma4:e4b

Tokens/sec32.953.0

First chunk3096 ms214 ms

TTFT3.1 s214 ms

Load timeN/A3.1 s

Memory usage2.5 GB15.0 GB

Memory %8%12%

HW Fit Score Breakdown

qwen3.5-2b-mlx

Speed

50/50

TTFT

13/20

Memory

30/30

gemma4:e4b

Speed

48/50

TTFT

20/20

Memory

30/30

Quality

qwen3.5-2b-mlx

Reasoning

11/20

Coding

9/20

Instruction

14/20

Structured

14/15

Math

3/15

Multilingual

9/10

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

gemma4:e4b

Reasoning

14/20

Coding

17/20

Instruction

15/20

Structured

15/15

Math

7/15

Multilingual

10/10

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

View qwen3.5-2b-mlx details | View gemma4:e4b 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