Back to leaderboard

gemma-4-31b-it-mlx

LM-STUDIO MLX

gemma4 · 31B · 8bit

Excellent

Aug 19, 2026 · Apple M4 Max

unsloth/qwen3.6-35b-a3b

LM-STUDIO GGUF

qwen35moe · 35B · Q3_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score
85 vs 85
Hardware Fit
64 vs 79
Quality Score
94 vs 88

Hardware

gemma-4-31b-it-mlx unsloth/qwen3.6-35…
MachineMacBook ProSystem manufacturer
CPUApple M4 MaxAMD Ryzen 7 5800X 8-Core Processor
Cores1616
RAM128 GB31 GB
GPUApple M4 MaxNavi 44 [Radeon RX 9060 XT]
OSmacOS 26.5.2Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedperformance

Performance

gemma-4-31b-it-mlx unsloth/qwen3.6-35…
Tokens/sec13.623.5
First chunk16 ms54 ms
TTFT558 ms457 ms
Load time12.3 sN/A
Memory usage0.0 GB18.3 GB
Memory %0%59%

HW Fit Score Breakdown

gemma-4-31b-it-mlx

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

unsloth/qwen3.6-35b-a3b

Speed
38/50
TTFT
20/20
Memory
21/30

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

unsloth/qwen3.6-35b-a3b

Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
View gemma-4-31b-it-mlx details | View unsloth/qwen3.6-35… 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