Back to leaderboard

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

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor

qwen3-4b-qwen3.6-plus-reasoning-distilled

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

Global Score
88 vs 65
Hardware Fit
94 vs 96
Quality Score
85 vs 51

Hardware

huihui-qwen3.6-35b… qwen3-4b-qwen3.6-p…
MachineGigabyte Technology Co., Ltd. B550M AORUS PROMac Studio
CPUAMD Ryzen 5 5600X 6-Core ProcessorApple M2 Max
Cores1212
RAM47 GB96 GB
GPUAD106 [GeForce RTX 4060 Ti]Apple M2 Max
OScachyos rollingmacOS 26.1
Archx64arm64
Power Modelow-powerbalanced

Performance

huihui-qwen3.6-35b… qwen3-4b-qwen3.6-p…
Tokens/sec39.899.6
First chunk3 ms18 ms
TTFT479 ms1.6 s
Load timeN/A4.8 s
Memory usage24.4 GB0.3 GB
Memory %52%0%

HW Fit Score Breakdown

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
20/20
Memory
24/30

qwen3-4b-qwen3.6-plus-r…

Speed
50/50
TTFT
16/20
Memory
30/30

Quality

huihui-qwen3.6-35b-a3b-…

Reasoning
18/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

qwen3-4b-qwen3.6-plus-r…

Reasoning
8/20
Coding
4/20
Instruction
14/20
Structured
9/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Adequate 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