GPT-120B:120b
gptoss · 116.8B · MXFP4
THINKING MODEL
HP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML (NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core ))
55 GB · Microsoft Windows 11 Pro 10.0.28000
Tested on August 22, 2026
Global Score
66 /100
Not Rec.
Hardware Fit
23/100
Quality
84/100
Get this model
Hardware
- Machine
- HP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
- CPU
- NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
- Cores
- 20 total (20 perf)
- Frequency
- 4 GHz
- RAM
- 55 GB LPDDR5
- GPU
- NVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
- OS
- Microsoft Windows 11 Pro 10.0.28000
- Arch
- arm64
- Power Mode
- balanced
Performance
- Tokens/sec
- 16.8
- Standard deviation
- ±1.7
- First chunk latency
- 11.2 s
- Time to first token
- 12.2 s
- Load time
- 77.3 s
- Memory usage
- 61.6 GB (113%)
- Total tokens
- 1486
- Thinking tokens (est.)
- ~279
Score breakdown
Speed
21/50
Time to first token
2/20
Memory
0/30
Quality
Reasoning
16/20
Coding
19/20
Instruction following
11/20
Structured output
13/15
Math
15/15
Multilingual
10/10
Category levels
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
Metadata
- Spec version
- 0.2.1
- Runtime
- Ollama 0.32.15
- Model format
- GGUF
- Hardware profile
- HIGH-END
- Result hash
- 0a7555f524434f952d40354b25b9a2fe3b297e0665fca30837e2b6c2d5aa5de5
Interpretation
Hardware fit: 23/100. Overall suitability: NOT RECOMMENDED (Global 66/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Adequate, Structured Output: Strong, Math: Strong, Multilingual: Strong.
Warnings
- CPU appears throttled (2.9 GHz current vs 4.0 GHz nominal, 73%).
- Significant swap activity during benchmark (+8.7 GB). Model may exceed available RAM — results are severely degraded.
Disqualifiers
- Memory usage critical: model delta +113%
Bench Environment
Power: AC Swap delta:
+8.7 GB
CPU load: avg 25% (peak 37%)
Run yours now
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest