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

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Not Rec.

Jul 17, 2026 · Apple M5 Max

Global Score
88 vs 80
Hardware Fit
85 vs 77
Quality Score
89 vs 81

Hardware

huihui-qwen3.6-35b… qwen3.6:35b-mlx
MachineGigabyte Technology Co., Ltd. B550M AORUS PROMacBook Pro
CPUAMD Ryzen 5 5600X 6-Core ProcessorApple M5 Max
Cores1218
RAM47 GB48 GB
GPUAD106 [GeForce RTX 4060 Ti]Apple M5 Max
OScachyos rollingmacOS 26.5.2
Archx64arm64
Power Modelow-powerbalanced

Performance

huihui-qwen3.6-35b… qwen3.6:35b-mlx
Tokens/sec37.7129.8
First chunk18 ms77 ms
TTFT2.9 s30.0 s
Load timeN/A1.8 s
Memory usage26.1 GB19.7 GB
Memory %56%41%

HW Fit Score Breakdown

huihui-qwen3.6-35b-a3b-…

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

qwen3.6:35b-mlx

Speed
50/50
TTFT
0/20
Memory
27/30

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

qwen3.6:35b-mlx

Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate Math: Strong Multilingual: Strong
View huihui-qwen3.6-35b… details | View qwen3.6:35b-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