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

qwen3:8b

OLLAMA GGUF

qwen3 · 8.2B · Q4_K_M

Excellent

Apr 28, 2026 · Intel Xeon® Gold 6230

Global Score
88 vs 80
Hardware Fit
85 vs 85
Quality Score
89 vs 78

Hardware

huihui-qwen3.6-35b… qwen3:8b
MachineGigabyte Technology Co., Ltd. B550M AORUS PROHP HP Z8 G4 Workstation
CPUAMD Ryzen 5 5600X 6-Core ProcessorIntel Xeon® Gold 6230
Cores1280
RAM47 GB252 GB
GPUAD106 [GeForce RTX 4060 Ti]TU104GL [Quadro RTX 5000]
OScachyos rollingUbuntu 24.04.4 LTS
Archx64x64
Power Modelow-powerlow-power

Performance

huihui-qwen3.6-35b… qwen3:8b
Tokens/sec37.765.1
First chunk18 ms289 ms
TTFT2.9 s4.2 s
Load timeN/A4.6 s
Memory usage26.1 GB5.6 GB
Memory %56%2%

HW Fit Score Breakdown

huihui-qwen3.6-35b-a3b-…

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

qwen3:8b

Speed
50/50
TTFT
5/20
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

qwen3:8b

Reasoning
17/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Adequate 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