gemma-4-31b-it-mlx

LM-STUDIO MLX

gemma4 · 31B · 8bit

Excellent

Aug 19, 2026 · Apple M4 Max

qwen2.5:3b

OLLAMA GGUF

qwen2 · 3.1B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

Global Score

85 vs 77

Hardware Fit

64 vs 100

Quality Score

94 vs 67

Hardware

gemma-4-31b-it-mlx qwen2.5:3b

MachineMacBook ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super

CPUApple M4 MaxCortex-A78AE

Cores166

RAM128 GB7 GB

GPUApple M4 MaxIntegrated / Unknown

OSmacOS 26.5.2Ubuntu 22.04.5 LTS

Archarm64arm64

Power Modebalancedbalanced

Performance

gemma-4-31b-it-mlx qwen2.5:3b

Tokens/sec13.621.4

First chunk16 ms1006 ms

TTFT558 ms1.0 s

Load time12.3 s6.4 s

Memory usage0.0 GB2.0 GB

Memory %0%27%

HW Fit Score Breakdown

gemma-4-31b-it-mlx

Speed

14/50

TTFT

20/20

Memory

30/30

qwen2.5:3b

Speed

50/50

TTFT

20/20

Memory

30/30

Quality

gemma-4-31b-it-mlx

Reasoning

19/20

Coding

19/20

Instruction

18/20

Structured

15/15

Math

14/15

Multilingual

9/10

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

qwen2.5:3b

Reasoning

12/20

Coding

14/20

Instruction

11/20

Structured

15/15

Math

6/15

Multilingual

9/10

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

View gemma-4-31b-it-mlx details | View qwen2.5:3b 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