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

qwen3:1.7b

OLLAMA GGUF

qwen3 · 2.0B · Q4_K_M

Good

Mar 5, 2026 · AMD RYZEN AI MAX+ 395

Global Score
88 vs 72
Hardware Fit
85 vs 92
Quality Score
89 vs 63

Hardware

huihui-qwen3.6-35b… qwen3:1.7b
MachineGigabyte Technology Co., Ltd. B550M AORUS PROAZW GTR Pro
CPUAMD Ryzen 5 5600X 6-Core ProcessorAMD RYZEN AI MAX+ 395
Cores1232
RAM47 GB125 GB
GPUAD106 [GeForce RTX 4060 Ti]AMD Radeon 8060S
OScachyos rollingUbuntu 24.04.4 LTS
Archx64x64
Power Modelow-powerlow-power

Performance

huihui-qwen3.6-35b… qwen3:1.7b
Tokens/sec37.7120.7
First chunk18 ms93 ms
TTFT2.9 s1.5 s
Load timeN/A2.5 s
Memory usage26.1 GB5.8 GB
Memory %56%5%

HW Fit Score Breakdown

huihui-qwen3.6-35b-a3b-…

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

qwen3:1.7b

Speed
50/50
TTFT
12/20
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

qwen3:1.7b

Reasoning
13/20
Coding
6/20
Instruction
13/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View huihui-qwen3.6-35b… details | View qwen3:1.7b 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