GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
qwen3-coder:latest
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
Global Score
66 vs 76
Hardware Fit
14 vs 51
Quality Score
88 vs 87
Hardware
GPT-120B:120b qwen3-coder:latest
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCDell Inc. Inspiron 15 3530
CPUIntel Core™ i7-14700FIntel Gen Intel® Core™ i7-1355U
Cores2812
RAM64 GB31 GB
GPUNVIDIA GeForce RTX 5080Raptor Lake-P [Iris Xe Graphics]
OSMicrosoft Windows 11 Enterprise 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power
Performance
GPT-120B:120b qwen3-coder:latest
Tokens/sec10.17.6
First chunk6562 ms2037 ms
TTFT10.3 s2.0 s
Load time49.8 s8.7 s
Memory usage61.5 GB18.9 GB
Memory %96%61%
HW Fit Score Breakdown
GPT-120B:120b
Speed
10/50
TTFT
2/20
Memory
2/30
qwen3-coder:latest
Speed
13/50
TTFT
18/20
Memory
20/30
Quality
GPT-120B:120b
Reasoning
18/20
Coding
19/20
Instruction
11/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3-coder:latest
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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