GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
cogito:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Mar 6, 2026 · Apple M4
Global Score
79 vs 77
Hardware Fit
47 vs 92
Quality Score
93 vs 70
Hardware
GPT-120B:120b cogito:8b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Air
CPUIntel Core™ i7-14700FApple M4
Cores2810
RAM128 GB32 GB
GPUNVIDIA GeForce RTX 5080Apple M4
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
GPT-120B:120b cogito:8b
Tokens/sec18.221.0
First chunk1719 ms312 ms
TTFT3.9 s312 ms
Load time50.9 s0.8 s
Memory usage61.5 GB10.4 GB
Memory %48%33%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
cogito:8b
Speed
42/50
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
cogito:8b
Reasoning
14/20
Coding
13/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak 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