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 )
phi4:latest
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
90 vs 85
Hardware Fit
96 vs 100
Quality Score
88 vs 79
Hardware
Kimi-48B:48B phi4:latest
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Intel Core™ i5-14400F
Cores2016
RAM55 GB32 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUNVIDIA GeForce RTX 5060 Ti
OSMicrosoft Windows 11 Pro 10.0.28000Microsoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
Kimi-48B:48B phi4:latest
Tokens/sec62.738.3
First chunk397 ms72 ms
TTFT397 ms72 ms
Load time16.8 s6.2 s
Memory usage25.5 GB9.1 GB
Memory %47%29%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
50/50
TTFT
20/20
Memory
26/30
phi4:latest
Speed
50/50
TTFT
20/20
Memory
30/30
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
phi4:latest
Reasoning
18/20
Coding
19/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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