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 )
Ling-3.0-tiny-IQ4_XS:latest
OLLAMA GGUFbailingmoe3 · 7.9B · IQ4_XS
Aug 30, 2026 · Intel Core™ i7-7700HQ
Global Score
66 vs 87
Hardware Fit
23 vs 100
Quality Score
84 vs 82
Hardware
GPT-120B:120b Ling-3.0-tiny-IQ4_…
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLASUSTeK COMPUTER INC. GL702VMK
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Intel Core™ i7-7700HQ
Cores208
RAM55 GB16 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUNVIDIA GeForce GTX 1060
OSMicrosoft Windows 11 Pro 10.0.28000Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
GPT-120B:120b Ling-3.0-tiny-IQ4_…
Tokens/sec16.824.7
First chunk11247 ms283 ms
TTFT12.2 s283 ms
Load time77.3 s45.8 s
Memory usage61.6 GB4.3 GB
Memory %113%27%
HW Fit Score Breakdown
GPT-120B:120b
Speed
21/50
TTFT
2/20
Memory
0/30
Ling-3.0-tiny-IQ4_XS:la…
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
Ling-3.0-tiny-IQ4_XS:la…
Reasoning
17/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
9/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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