deepseek-v2:16b
OLLAMA GGUFdeepseek2 · 15.7B · Q4_0
Mar 2, 2026 · Apple M4
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 )
Global Score
69 vs 66
Hardware Fit
100 vs 23
Quality Score
55 vs 84
Hardware
deepseek-v2:16b GPT-120B:120b
MachineMacBook AirHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUApple M4NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores1020
RAM32 GB55 GB
GPUApple M4NVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.28000
Archarm64arm64
Power Modebalancedbalanced
Performance
deepseek-v2:16b GPT-120B:120b
Tokens/sec56.616.8
First chunkN/A11247 ms
TTFT239 ms12.2 s
Load time1.2 s77.3 s
Memory usage17.7 GB61.6 GB
Memory %55%113%
HW Fit Score Breakdown
deepseek-v2:16b
Speed
40/50
TTFT
30/20
Memory
30/30
GPT-120B:120b
Speed
21/50
TTFT
2/20
Memory
0/30
Quality
deepseek-v2:16b
Reasoning
7/20
Coding
9/20
Instruction
13/20
Structured
10/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Adequate Multilingual: Strong
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
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