GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 18, 2026 · Intel Core™ i7-14700F
qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
Global Score
79 vs 59
Hardware Fit
47 vs 63
Quality Score
93 vs 58
Hardware
GPT-120B:120b qwen3.8-27b-mlx
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Pro
CPUIntel Core™ i7-14700FApple M5 Max
Cores2818
RAM128 GB64 GB
GPUNVIDIA GeForce RTX 5080Apple M5 Max
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 27.0
Archx64arm64
Power Modebalancedbalanced
Performance
GPT-120B:120b qwen3.8-27b-mlx
Tokens/sec18.218.3
First chunk1719 ms4 ms
TTFT3.9 s530 ms
Load time50.9 sN/A
Memory usage61.5 GB38.5 GB
Memory %48%60%
HW Fit Score Breakdown
GPT-120B:120b
Speed
17/50
TTFT
5/20
Memory
25/30
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
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
qwen3.8-27b-mlx
Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
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