GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
qwen3.6:35b-mlx
OLLAMA GGUFnvfp4
Jul 17, 2026 · Apple M5 Max
Global Score
79 vs 80
Hardware Fit
47 vs 77
Quality Score
93 vs 81
Hardware
GPT-120B:120b qwen3.6:35b-mlx
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Pro
CPUIntel Core™ i7-14700FApple M5 Max
Cores2818
RAM128 GB48 GB
GPUNVIDIA GeForce RTX 5080Apple M5 Max
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 26.5.2
Archx64arm64
Power Modebalancedbalanced
Performance
GPT-120B:120b qwen3.6:35b-mlx
Tokens/sec18.2129.8
First chunk1719 ms77 ms
TTFT3.9 s30.0 s
Load time50.9 s1.8 s
Memory usage61.5 GB19.7 GB
Memory %48%41%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
qwen3.6:35b-mlx
Speed
50/50
TTFT
0/20
Memory
27/30
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-mlx
Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate 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