GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
qwen3.6-35b-a3b
LM-STUDIO GGUFqwen35moe · 35B · IQ3_XXS
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
Global Score
79 vs 79
Hardware Fit
47 vs 59
Quality Score
93 vs 87
Hardware
GPT-120B:120b qwen3.6-35b-a3b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCDocker Container
CPUIntel Core™ i7-14700FIntel Gen Intel® Core™ i9-11900H
Cores2816
RAM128 GB15 GB
GPUNVIDIA GeForce RTX 5080TigerLake-H GT1 [UHD Graphics]
OSMicrosoft Windows 11 Enterprise 10.0.26200Ubuntu 26.04 LTS
Archx64x64
Power Modebalancedperformance
Performance
GPT-120B:120b qwen3.6-35b-a3b
Tokens/sec18.29.3
First chunk1719 ms21 ms
TTFT3.9 s3.6 s
Load time50.9 s32.0 s
Memory usage61.5 GB1.8 GB
Memory %48%12%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
qwen3.6-35b-a3b
Speed
17/50
TTFT
12/20
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
qwen3.6-35b-a3b
Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
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