GPT-120B:120b
OLLAMA GGUFgptoss · 116.8B · MXFP4
Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
qwen3.5-4b-mlx
LM-STUDIO MLXqwen3_5 · 4B · 4bit
Mar 6, 2026 · Apple M4 Pro
Global Score
66 vs 62
Hardware Fit
23 vs 35
Quality Score
84 vs 73
Hardware
GPT-120B:120b qwen3.5-4b-mlx
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLMac mini
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Apple M4 Pro
Cores2014
RAM55 GB64 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.28000macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced
Performance
GPT-120B:120b qwen3.5-4b-mlx
Tokens/sec16.80.0
First chunk11247 ms5548 ms
TTFT12.2 s5.5 s
Load time77.3 sN/A
Memory usage61.6 GB2.9 GB
Memory %113%5%
HW Fit Score Breakdown
GPT-120B:120b
Speed
21/50
TTFT
2/20
Memory
0/30
qwen3.5-4b-mlx
Speed
0/50
TTFT
6/20
Memory
29/30
Quality
GPT-120B:120b
Reasoning
16/20
Coding
19/20
Instruction
11/20
Structured
13/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
qwen3.5-4b-mlx
Reasoning
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak 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