Back to leaderboard

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

gemma-4-31b-it-mlx

LM-STUDIO MLX

gemma4 · 31B · 8bit

Excellent

Aug 19, 2026 · Apple M4 Max

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

Hardware

huihui-qwen3.6-35b… gemma-4-31b-it-mlx
MachineGigabyte Technology Co., Ltd. B550M AORUS PROMacBook Pro
CPUAMD Ryzen 5 5600X 6-Core ProcessorApple M4 Max
Cores1216
RAM47 GB128 GB
GPUAD106 [GeForce RTX 4060 Ti]Apple M4 Max
OScachyos rollingmacOS 26.5.2
Archx64arm64
Power Modelow-powerbalanced

Performance

huihui-qwen3.6-35b… gemma-4-31b-it-mlx
Tokens/sec37.713.6
First chunk18 ms16 ms
TTFT2.9 s558 ms
Load timeN/A12.3 s
Memory usage26.1 GB0.0 GB
Memory %56%0%

HW Fit Score Breakdown

huihui-qwen3.6-35b-a3b-…

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

gemma-4-31b-it-mlx

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

Quality

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

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
View huihui-qwen3.6-35b… details | View gemma-4-31b-it-mlx 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