GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
qwen3.5:35b-a3b-q4_K_M
OLLAMA GGUFqwen35moe · 36.0B · Q4_K_M
Aug 22, 2026 · Intel Xeon® E5-2637 v3
Global Score
79 vs 90
Hardware Fit
47 vs 98
Quality Score
93 vs 86
Hardware
GPT-120B:120b qwen3.5:35b-a3b-q4…
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCDell Inc. Precision Tower 7910
CPUIntel Core™ i7-14700FIntel Xeon® E5-2637 v3
Cores2816
RAM128 GB96 GB
GPUNVIDIA GeForce RTX 5080NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3060
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows 10 Pro 10.0.19045
Archx64x64
Power Modebalancedbalanced
Performance
GPT-120B:120b qwen3.5:35b-a3b-q4…
Tokens/sec18.247.1
First chunk1719 ms1063 ms
TTFT3.9 s1.1 s
Load time50.9 s17.3 s
Memory usage61.5 GB22.9 GB
Memory %48%24%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
qwen3.5:35b-a3b-q4_K_M
Speed
50/50
TTFT
18/20
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
qwen3.5:35b-a3b-q4_K_M
Reasoning
16/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
11/15
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