GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
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
Global Score
66 vs 88
Hardware Fit
23 vs 85
Quality Score
84 vs 89
Hardware
GPT-120B:120b huihui-qwen3.6-35b…
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLGigabyte Technology Co., Ltd. B550M AORUS PRO
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )AMD Ryzen 5 5600X 6-Core Processor
Cores2012
RAM55 GB47 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUAD106 [GeForce RTX 4060 Ti]
OSMicrosoft Windows 11 Pro 10.0.28000cachyos rolling
Archarm64x64
Power Modebalancedlow-power
Performance
GPT-120B:120b huihui-qwen3.6-35b…
Tokens/sec16.837.7
First chunk11247 ms18 ms
TTFT12.2 s2.9 s
Load time77.3 sN/A
Memory usage61.6 GB26.1 GB
Memory %113%56%
HW Fit Score Breakdown
GPT-120B:120b
Speed
21/50
TTFT
2/20
Memory
0/30
huihui-qwen3.6-35b-a3b-…
Speed
50/50
TTFT
13/20
Memory
22/30
Quality
GPT-120B:120b
Reasoning
16/20
Coding
19/20
Instruction
11/20
Structured
13/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
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
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