hermes3:8b
OLLAMA GGUFllama · 8.0B · Q4_0
Mar 6, 2026 · Apple M4
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Global Score
74 vs 93
Hardware Fit
94 vs 91
Quality Score
65 vs 94
Hardware
hermes3:8b GPT-20B:20b
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
hermes3:8b GPT-20B:20b
Tokens/sec22.357.8
First chunk296 ms203 ms
TTFT296 ms3.0 s
Load time0.8 s19.2 s
Memory usage10.2 GB12.0 GB
Memory %32%22%
HW Fit Score Breakdown
hermes3:8b
Speed
44/50
TTFT
20/20
Memory
30/30
GPT-20B:20b
Speed
50/50
TTFT
11/20
Memory
30/30
Quality
hermes3:8b
Reasoning
11/20
Coding
10/20
Instruction
14/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
GPT-20B:20b
Reasoning
19/20
Coding
17/20
Instruction
18/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong 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