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

qwen3.5:0.8b

OLLAMA GGUF

qwen35 · 873.44M · Q8_0

Not Rec.

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score
88 vs 18
Hardware Fit
85 vs 53
Quality Score
89 vs 3

Hardware

huihui-qwen3.6-35b… qwen3.5:0.8b
MachineGigabyte Technology Co., Ltd. B550M AORUS PROLENOVO 20L7CTO1WW
CPUAMD Ryzen 5 5600X 6-Core ProcessorIntel Core™ i5-8350U
Cores128
RAM47 GB23 GB
GPUAD106 [GeForce RTX 4060 Ti]Kaby Lake-R GT2 [UHD Graphics 620]
OScachyos rollingFedora Linux 43
Archx64x64
Power Modelow-powerlow-power

Performance

huihui-qwen3.6-35b… qwen3.5:0.8b
Tokens/sec37.79.4
First chunk18 ms799 ms
TTFT2.9 s30.0 s
Load timeN/A3.3 s
Memory usage26.1 GB1.9 GB
Memory %56%8%

HW Fit Score Breakdown

huihui-qwen3.6-35b-a3b-…

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

qwen3.5:0.8b

Speed
23/50
TTFT
0/20
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

qwen3.5:0.8b

Reasoning
0/20
Coding
0/20
Instruction
2/20
Structured
0/15
Math
0/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
View huihui-qwen3.6-35b… details | View qwen3.5:0.8b details

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