granite3.1-moe:3b
OLLAMA GGUFgranitemoe · 3.3B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
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
66 vs 66
Hardware Fit
99 vs 23
Quality Score
52 vs 84
Hardware
granite3.1-moe:3b GPT-120B:120b
MachineDell Inc. Inspiron 15 3530HP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUIntel Gen Intel® Core™ i7-1355UNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores1220
RAM31 GB55 GB
GPURaptor Lake-P [Iris Xe Graphics]NVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OScachyos rollingMicrosoft Windows 11 Pro 10.0.28000
Archx64arm64
Power Modelow-powerbalanced
Performance
granite3.1-moe:3b GPT-120B:120b
Tokens/sec27.216.8
First chunk527 ms11247 ms
TTFT527 ms12.2 s
Load time1.9 s77.3 s
Memory usage2.9 GB61.6 GB
Memory %9%113%
HW Fit Score Breakdown
granite3.1-moe:3b
Speed
49/50
TTFT
20/20
Memory
30/30
GPT-120B:120b
Speed
21/50
TTFT
2/20
Memory
0/30
Quality
granite3.1-moe:3b
Reasoning
7/20
Coding
9/20
Instruction
13/20
Structured
12/15
Math
5/15
Multilingual
6/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate
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