Kimi-48B:48B

kimi-linear · 49.1B · unknown

GMKtec NucBox EVO-T2S (Intel Core™ Ultra X7 358H)

64 GB · Microsoft Windows 11 Pro 10.0.26200

Tested on August 24, 2026 · Submitted by Haval

Top 22% Compare

Global Score

86 /100

Excellent

Hardware Fit

78/100

Quality

89/100

Get this model

🦙

Ollama

ollama pull Kimi-48B:48B

View on Ollama Library

ollama.com/library/Kimi-48B

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: GMKtec NucBox EVO-T2S
CPU: Intel Core™ Ultra X7 358H
Cores: 16 total (16 perf)
Frequency: 1.9 GHz
RAM: 64 GB LPDDR5
GPU: Intel(R) Arc(TM) B390 GPU
OS: Microsoft Windows 11 Pro 10.0.26200
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 23.1
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.1
First chunk latency Delay before the first streamed chunk arrives from runtime: 752 ms
Time to first token How fast the model starts responding — lower is better: 752 ms
Load time Time to load the model into memory before inference: 22.2 s
Memory usage RAM consumed during inference — percentage of total system memory: 25.5 GB (40%)
Total tokens Total number of tokens generated across all benchmark prompts: 1069

Score breakdown

Speed

31/50

Time to first token

20/20

Memory

27/30

Quality

Reasoning

18/20

Coding

19/20

Instruction following

15/20

Structured output

15/15

Math

13/15

Multilingual

9/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.32.14
Model format: GGUF
Hardware profile: HIGH-END
Result hash: a2c11dd0c058cf42742419b1f31a2b13696844ffb185181383798efa304759ab

Interpretation

Hardware fit: 78/100. Overall suitability: EXCELLENT (Global 86/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Bench Environment

CPU load: avg 41% (peak 52%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest