phi4-mini:latest
OLLAMA GGUFphi3 · 3.8B · Q4_K_M
Mar 2, 2026 · Apple M4
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 )
Global Score
71 vs 90
Hardware Fit
100 vs 96
Quality Score
58 vs 88
Hardware
phi4-mini:latest Kimi-48B:48B
MachineMacBook AirHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUApple M4NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores1020
RAM32 GB55 GB
GPUApple M4NVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.28000
Archarm64arm64
Power Modebalancedbalanced
Performance
phi4-mini:latest Kimi-48B:48B
Tokens/sec36.262.7
First chunkN/A397 ms
TTFT190 ms397 ms
Load time0.8 s16.8 s
Memory usage8.3 GB25.5 GB
Memory %26%47%
HW Fit Score Breakdown
phi4-mini:latest
Speed
40/50
TTFT
30/20
Memory
30/30
Kimi-48B:48B
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
phi4-mini:latest
Reasoning
12/20
Coding
10/20
Instruction
10/20
Structured
11/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Strong
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
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