Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

google/gemma-3-4b

LM-STUDIO MLX

gemma3 · 4B · 4bit

Good

Mar 3, 2026 · Apple M4

Global Score

90 vs 76

Hardware Fit

96 vs 100

Quality Score

88 vs 66

Hardware

Kimi-48B:48B google/gemma-3-4b

MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLMacBook Air

CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Apple M4

Cores2010

RAM55 GB32 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 google/gemma-3-4b

Tokens/sec62.739.4

First chunk397 ms468 ms

TTFT397 ms468 ms

Load time16.8 sN/A

Memory usage25.5 GB2.8 GB

Memory %47%9%

HW Fit Score Breakdown

Kimi-48B:48B

Speed

50/50

TTFT

20/20

Memory

26/30

google/gemma-3-4b

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

google/gemma-3-4b

Reasoning

10/20

Coding

17/20

Instruction

13/20

Structured

12/15

Math

4/15

Multilingual

10/10

Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong

View Kimi-48B:48B details | View google/gemma-3-4b details

Run yours and compare

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest