Back to leaderboard

GPT-120B:120b

OLLAMA GGUF

gptoss · 116.8B · MXFP4

Not Rec.

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

gemma3n:latest

OLLAMA GGUF

gemma3n · 6.9B · Q4_K_M

Excellent

Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor

Global Score
66 vs 81
Hardware Fit
23 vs 100
Quality Score
84 vs 73

Hardware

GPT-120B:120b gemma3n:latest
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLSupermicro AS -2015HS-TNR
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )AMD EPYC 9654P 96-Core Processor
Cores2064
RAM55 GB128 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSMicrosoft Windows 11 Pro 10.0.28000Ubuntu 24.04.3 LTS
Archarm64x64
Power Modebalancedperformance

Performance

GPT-120B:120b gemma3n:latest
Tokens/sec16.8108.7
First chunk11247 ms333 ms
TTFT12.2 s333 ms
Load time77.3 s4.5 s
Memory usage61.6 GB8.6 GB
Memory %113%7%

HW Fit Score Breakdown

GPT-120B:120b

Speed
21/50
TTFT
2/20
Memory
0/30

gemma3n:latest

Speed
50/50
TTFT
20/20
Memory
30/30

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

gemma3n:latest

Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest