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 )
gemma4:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Apr 3, 2026 · Apple M4
Global Score
90 vs 85
Hardware Fit
96 vs 77
Quality Score
88 vs 89
Hardware
Kimi-48B:48B gemma4:26b
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLMac mini
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Apple M4
Cores2010
RAM55 GB24 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUApple M4
OSMicrosoft Windows 11 Pro 10.0.28000macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
Kimi-48B:48B gemma4:26b
Tokens/sec62.724.5
First chunk397 ms1481 ms
TTFT397 ms1.5 s
Load time16.8 s24.7 s
Memory usage25.5 GB20.3 GB
Memory %47%85%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
50/50
TTFT
20/20
Memory
26/30
gemma4:26b
Speed
49/50
TTFT
20/20
Memory
8/30
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
gemma4:26b
Reasoning
17/20
Coding
19/20
Instruction
17/20
Structured
14/15
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