GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
Qwen3.8-27B-Opus-Distill-IQ3_XXS:latest
OLLAMA GGUFqwen35 · 27.3B · IQ3_XXS
Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor
Global Score
79 vs 73
Hardware Fit
47 vs 98
Quality Score
93 vs 62
Hardware
GPT-120B:120b Qwen3.8-27B-Opus-D…
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 Qwen3.8-27B-Opus-D…
Tokens/sec18.261.4
First chunk1719 ms381 ms
TTFT3.9 s381 ms
Load time50.9 s0.2 s
Memory usage61.5 GB12.2 GB
Memory %48%39%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
Qwen3.8-27B-Opus-Distil…
Speed
50/50
TTFT
20/20
Memory
28/30
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
Qwen3.8-27B-Opus-Distil…
Reasoning
17/20
Coding
18/20
Instruction
8/20
Structured
0/15
Math
13/15
Multilingual
6/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Adequate
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