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-vl:30b

OLLAMA GGUF

qwen3vlmoe · 31.1B · Q4_K_M

Excellent

Mar 5, 2026 · Intel Core™ Ultra 9 285K

Global Score
88 vs 80
Hardware Fit
94 vs 98
Quality Score
85 vs 72

Hardware

huihui-qwen3.6-35b… qwen3-vl:30b
MachineGigabyte Technology Co., Ltd. B550M AORUS PROASUS
CPUAMD Ryzen 5 5600X 6-Core ProcessorIntel Core™ Ultra 9 285K
Cores1224
RAM47 GB47 GB
GPUAD106 [GeForce RTX 4060 Ti]NVIDIA GeForce RTX 5090, Intel(R) Graphics
OScachyos rollingMicrosoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

huihui-qwen3.6-35b… qwen3-vl:30b
Tokens/sec39.8208.9
First chunk3 ms102 ms
TTFT479 ms684 ms
Load timeN/A0.1 s
Memory usage24.4 GB22.0 GB
Memory %52%47%

HW Fit Score Breakdown

huihui-qwen3.6-35b-a3b-…

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

qwen3-vl:30b

Speed
50/50
TTFT
20/20
Memory
28/30

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-vl:30b

Reasoning
14/20
Coding
6/20
Instruction
17/20
Structured
12/15
Math
13/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak 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