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-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K

Global Score
88 vs 80
Hardware Fit
85 vs 60
Quality Score
89 vs 88

Hardware

huihui-qwen3.6-35b… qwen3-coder:30b
MachineGigabyte Technology Co., Ltd. B550M AORUS PROASUS
CPUAMD Ryzen 5 5600X 6-Core ProcessorIntel Gen Intel® Core™ i7-12700K
Cores1220
RAM47 GB96 GB
GPUAD106 [GeForce RTX 4060 Ti]Parsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OScachyos rollingMicrosoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

huihui-qwen3.6-35b… qwen3-coder:30b
Tokens/sec37.714.7
First chunk18 ms796 ms
TTFT2.9 s796 ms
Load timeN/A0.2 s
Memory usage26.1 GB17.9 GB
Memory %56%19%

HW Fit Score Breakdown

huihui-qwen3.6-35b-a3b-…

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

qwen3-coder:30b

Speed
14/50
TTFT
19/20
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-coder:30b

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong 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