Back to leaderboard

gemma-4-31b-it-mlx

LM-STUDIO MLX

gemma4 · 31B · 8bit

Excellent

Aug 19, 2026 · Apple M4 Max

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor

Global Score
85 vs 88
Hardware Fit
64 vs 85
Quality Score
94 vs 89

Hardware

gemma-4-31b-it-mlx huihui-qwen3.6-35b…
MachineMacBook ProGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUApple M4 MaxAMD Ryzen 5 5600X 6-Core Processor
Cores1612
RAM128 GB47 GB
GPUApple M4 MaxAD106 [GeForce RTX 4060 Ti]
OSmacOS 26.5.2cachyos rolling
Archarm64x64
Power Modebalancedlow-power

Performance

gemma-4-31b-it-mlx huihui-qwen3.6-35b…
Tokens/sec13.637.7
First chunk16 ms18 ms
TTFT558 ms2.9 s
Load time12.3 sN/A
Memory usage0.0 GB26.1 GB
Memory %0%56%

HW Fit Score Breakdown

gemma-4-31b-it-mlx

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

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
13/20
Memory
22/30

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

huihui-qwen3.6-35b-a3b-…

Reasoning
19/20
Coding
15/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong 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