GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
qwen3.5:4b
OLLAMA GGUFqwen35 · 4.7B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
Global Score
66 vs 83
Hardware Fit
14 vs 100
Quality Score
88 vs 76
Hardware
GPT-120B:120b qwen3.5:4b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Pro
CPUIntel Core™ i7-14700FApple M1 Max
Cores2810
RAM64 GB32 GB
GPUNVIDIA GeForce RTX 5080Apple M1 Max
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
GPT-120B:120b qwen3.5:4b
Tokens/sec10.133.8
First chunk6562 ms293 ms
TTFT10.3 s293 ms
Load time49.8 s2.5 s
Memory usage61.5 GB6.5 GB
Memory %96%20%
HW Fit Score Breakdown
GPT-120B:120b
Speed
10/50
TTFT
2/20
Memory
2/30
qwen3.5:4b
Speed
50/50
TTFT
20/20
Memory
30/30
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
qwen3.5:4b
Reasoning
16/20
Coding
14/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong 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