Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
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
90 vs 66
Hardware Fit
96 vs 23
Quality Score
88 vs 84
Hardware
Kimi-48B:48B GPT-120B:120b
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores2020
RAM55 GB55 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSMicrosoft Windows 11 Pro 10.0.28000Microsoft Windows 11 Pro 10.0.28000
Archarm64arm64
Power Modebalancedbalanced
Performance
Kimi-48B:48B GPT-120B:120b
Tokens/sec62.716.8
First chunk397 ms11247 ms
TTFT397 ms12.2 s
Load time16.8 s77.3 s
Memory usage25.5 GB61.6 GB
Memory %47%113%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
50/50
TTFT
20/20
Memory
26/30
GPT-120B:120b
Speed
21/50
TTFT
2/20
Memory
0/30
Quality
Kimi-48B:48B
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
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