huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp
LM-STUDIO GGUFqwen35moe · 35B · Q4_K
Jun 13, 2026 · AMD Ryzen 5 5600X 6-Core Processor
qwen3.5:122b-a10b
OLLAMA GGUFqwen35moe · 125.1B · Q4_K_M
Mar 12, 2026 · AMD RYZEN AI MAX+ 395
Global Score
88 vs 80
Hardware Fit
85 vs 52
Quality Score
89 vs 92
Hardware
huihui-qwen3.6-35b… qwen3.5:122b-a10b
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]Radeon 8060S
OScachyos rollingUbuntu 24.04.4 LTS
Archx64x64
Power Modelow-powerperformance
Performance
huihui-qwen3.6-35b… qwen3.5:122b-a10b
Tokens/sec37.719.1
First chunk18 ms467 ms
TTFT2.9 s467 ms
Load timeN/A30.0 s
Memory usage26.1 GB89.3 GB
Memory %56%72%
HW Fit Score Breakdown
huihui-qwen3.6-35b-a3b-…
Speed
50/50
TTFT
13/20
Memory
22/30
qwen3.5:122b-a10b
Speed
18/50
TTFT
20/20
Memory
14/30
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
qwen3.5:122b-a10b
Reasoning
19/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
13/15
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest