gemma4:latest
OLLAMA GGUFgemma4 · 8.0B · Q4_K_M
Jun 5, 2026 · AMD Ryzen 7 5800H
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
89 vs 90
Hardware Fit
83 vs 96
Quality Score
92 vs 88
Hardware
gemma4:latest Kimi-48B:48B
MachineLENOVO 82JQHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUAMD Ryzen 7 5800HNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores1620
RAM16 GB55 GB
GPUNVIDIA GeForce RTX 3060 Laptop GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSMicrosoft Windows 11 家庭版 中文版 10.0.26100Microsoft Windows 11 Pro 10.0.28000
Archx64arm64
Power Modebalancedbalanced
Performance
gemma4:latest Kimi-48B:48B
Tokens/sec46.362.7
First chunk824 ms397 ms
TTFT3.8 s397 ms
Load time21.0 s16.8 s
Memory usage8.9 GB25.5 GB
Memory %56%47%
HW Fit Score Breakdown
gemma4:latest
Speed
50/50
TTFT
11/20
Memory
22/30
Kimi-48B:48B
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
gemma4:latest
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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