GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
qwen3.8-9b-heretic-uncensored-nvfp4
LM-STUDIO GGUFqwen35 · 9B · Q8_0
Aug 20, 2026 · AMD Ryzen 7 9700X 8-Core Processor
Global Score
79 vs 82
Hardware Fit
47 vs 100
Quality Score
93 vs 74
Hardware
GPT-120B:120b qwen3.8-9b-heretic…
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMicro-Star International Co., Ltd. MS-7E51
CPUIntel Core™ i7-14700FAMD Ryzen 7 9700X 8-Core Processor
Cores2816
RAM128 GB31 GB
GPUNVIDIA GeForce RTX 5080NVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
GPT-120B:120b qwen3.8-9b-heretic…
Tokens/sec18.2130.1
First chunk1719 ms20 ms
TTFT3.9 s99 ms
Load time50.9 sN/A
Memory usage61.5 GB6.5 GB
Memory %48%21%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
qwen3.8-9b-heretic-unce…
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
GPT-120B:120b
Reasoning
19/20
Coding
19/20
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
qwen3.8-9b-heretic-unce…
Reasoning
14/20
Coding
14/20
Instruction
13/20
Structured
14/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Adequate 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