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

gpt-oss:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

Global Score
88 vs 94
Hardware Fit
85 vs 97
Quality Score
89 vs 93

Hardware

huihui-qwen3.6-35b… gpt-oss:20b
MachineGigabyte Technology Co., Ltd. B550M AORUS PROGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUAMD Ryzen 5 5600X 6-Core ProcessorIntel Core™ i5-14400F
Cores1216
RAM47 GB32 GB
GPUAD106 [GeForce RTX 4060 Ti]NVIDIA GeForce RTX 5060 Ti
OScachyos rollingMicrosoft Windows 11 Professionnel 10.0.26200
Archx64x64
Power Modelow-powerbalanced

Performance

huihui-qwen3.6-35b… gpt-oss:20b
Tokens/sec37.780.4
First chunk18 ms139 ms
TTFT2.9 s1.6 s
Load timeN/A11.6 s
Memory usage26.1 GB11.9 GB
Memory %56%37%

HW Fit Score Breakdown

huihui-qwen3.6-35b-a3b-…

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

gpt-oss:20b

Speed
50/50
TTFT
19/20
Memory
28/30

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

gpt-oss:20b

Reasoning
19/20
Coding
17/20
Instruction
17/20
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