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

GPT-OSS-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Aug 18, 2026 · Intel Core™ i7-14700F

Global Score
88 vs 93
Hardware Fit
94 vs 92
Quality Score
85 vs 93

Hardware

huihui-qwen3.6-35b… GPT-OSS-20B:20b
MachineGigabyte Technology Co., Ltd. B550M AORUS PROHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUAMD Ryzen 5 5600X 6-Core ProcessorIntel Core™ i7-14700F
Cores1228
RAM47 GB128 GB
GPUAD106 [GeForce RTX 4060 Ti]NVIDIA GeForce RTX 5080
OScachyos rollingMicrosoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

huihui-qwen3.6-35b… GPT-OSS-20B:20b
Tokens/sec39.8178.6
First chunk3 ms695 ms
TTFT479 ms1.4 s
Load timeN/A31.2 s
Memory usage24.4 GB11.9 GB
Memory %52%9%

HW Fit Score Breakdown

huihui-qwen3.6-35b-a3b-…

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

GPT-OSS-20B:20b

Speed
50/50
TTFT
12/20
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

GPT-OSS-20B:20b

Reasoning
19/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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