Back to leaderboard

gemma-4-31b-it-mlx

LM-STUDIO MLX

gemma4 · 31B · 8bit

Excellent

Aug 19, 2026 · Apple M4 Max

qwen3-4b-qwen3.6-plus-reasoning-distilled

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

Global Score
85 vs 65
Hardware Fit
64 vs 96
Quality Score
94 vs 51

Hardware

gemma-4-31b-it-mlx qwen3-4b-qwen3.6-p…
MachineMacBook ProMac Studio
CPUApple M4 MaxApple M2 Max
Cores1612
RAM128 GB96 GB
GPUApple M4 MaxApple M2 Max
OSmacOS 26.5.2macOS 26.1
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma-4-31b-it-mlx qwen3-4b-qwen3.6-p…
Tokens/sec13.699.6
First chunk16 ms18 ms
TTFT558 ms1.6 s
Load time12.3 s4.8 s
Memory usage0.0 GB0.3 GB
Memory %0%0%

HW Fit Score Breakdown

gemma-4-31b-it-mlx

Speed
14/50
TTFT
20/20
Memory
30/30

qwen3-4b-qwen3.6-plus-r…

Speed
50/50
TTFT
16/20
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

qwen3-4b-qwen3.6-plus-r…

Reasoning
8/20
Coding
4/20
Instruction
14/20
Structured
9/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Adequate Multilingual: Strong
View gemma-4-31b-it-mlx details | View qwen3-4b-qwen3.6-p… 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