Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Jul 7, 2026 · Cortex-X925

qwen3.5-4b-mlx

LM-STUDIO MLX

qwen3_5 · 4B · 4bit

Not Rec.

Mar 6, 2026 · Apple M4 Pro

Global Score
66 vs 62
Hardware Fit
40 vs 35
Quality Score
77 vs 73

Hardware

gemma4:31b qwen3.5-4b-mlx
MachineASUSTeK COMPUTER INC. GX10Mac mini
CPUCortex-X925Apple M4 Pro
Cores2014
RAM122 GB64 GB
GPUDevice 2e12Apple M4 Pro
OSUbuntu 24.04.4 LTSmacOS 15.7.4
Archarm64arm64
Power Modeperformancebalanced

Performance

gemma4:31b qwen3.5-4b-mlx
Tokens/sec10.70.0
First chunk983 ms5548 ms
TTFT20.3 s5.5 s
Load time8.8 sN/A
Memory usage21.4 GB2.9 GB
Memory %18%5%

HW Fit Score Breakdown

gemma4:31b

Speed
10/50
TTFT
0/20
Memory
30/30

qwen3.5-4b-mlx

Speed
0/50
TTFT
6/20
Memory
29/30

Quality

gemma4:31b

Reasoning
14/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3.5-4b-mlx

Reasoning
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong

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