Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 19, 2026 · Intel Core™ Ultra X7 358H

google/gemma-3-27b

LM-STUDIO MLX

gemma3 · 27B · 4bit

Not Rec.

Mar 19, 2026 · Apple M4

Global Score

86 vs 71

Hardware Fit

78 vs 35

Quality Score

89 vs 86

Hardware

Kimi-48B:48B google/gemma-3-27b

MachineGMKtec NucBox EVO-T2SMac mini

CPUIntel Core™ Ultra X7 358HApple M4

Cores1610

RAM64 GB24 GB

GPUIntel(R) Arc(TM) B390 GPUApple M4

OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.3

Archx64arm64

Power Modebalancedbalanced

Performance

Kimi-48B:48B google/gemma-3-27b

Tokens/sec22.85.9

First chunk721 ms19 ms

TTFT721 ms1.8 s

Load time23.0 sN/A

Memory usage25.5 GB22.0 GB

Memory %40%92%

HW Fit Score Breakdown

Kimi-48B:48B

Speed

31/50

TTFT

20/20

Memory

27/30

google/gemma-3-27b

Speed

12/50

TTFT

19/20

Memory

4/30

Quality

Kimi-48B:48B

Reasoning

18/20

Coding

19/20

Instruction

15/20

Structured

15/15

Math

13/15

Multilingual

9/10

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

google/gemma-3-27b

Reasoning

16/20

Coding

18/20

Instruction

16/20

Structured

15/15

Math

11/15

Multilingual

10/10

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

View Kimi-48B:48B details | View google/gemma-3-27b 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