Back to leaderboard

gemma-4-31b-it-mlx

LM-STUDIO MLX

gemma4 · 31B · 8bit

Excellent

Aug 19, 2026 · Apple M4 Max

Qwen3.6-35B-A3B-Q4_K_M:latest

OLLAMA GGUF

qwen35moe · 34.7B · Q4_K_M

Excellent

Aug 18, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
85 vs 86
Hardware Fit
64 vs 87
Quality Score
94 vs 86

Hardware

gemma-4-31b-it-mlx Qwen3.6-35B-A3B-Q4…
MachineMacBook ProMicro-Star International Co., Ltd. MS-7E51
CPUApple M4 MaxAMD Ryzen 7 9700X 8-Core Processor
Cores1616
RAM128 GB31 GB
GPUApple M4 MaxNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSmacOS 26.5.2Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

gemma-4-31b-it-mlx Qwen3.6-35B-A3B-Q4…
Tokens/sec13.692.9
First chunk16 ms362 ms
TTFT558 ms362 ms
Load time12.3 s12.3 s
Memory usage0.0 GB20.7 GB
Memory %0%67%

HW Fit Score Breakdown

gemma-4-31b-it-mlx

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

Qwen3.6-35B-A3B-Q4_K_M:…

Speed
50/50
TTFT
20/20
Memory
17/30

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

Qwen3.6-35B-A3B-Q4_K_M:…

Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
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