Kimi-48B:48B

kimi-linear · 49.1B · unknown

HP HyperX OMEN Gaming Laptop 16-ap1xxx (AMD Ryzen 9 9955HX3D 16-Core Processor)

31 GB · Microsoft Windows 11 Home 10.0.26200

Tested on August 19, 2026

Top 23% Compare

Global Score

85 /100

Excellent

Hardware Fit

78/100

Quality

88/100

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: HP HyperX OMEN Gaming Laptop 16-ap1xxx
CPU: AMD Ryzen 9 9955HX3D 16-Core Processor
Cores: 32 total (32 perf)
Frequency: 2.5 GHz
RAM: 31 GB DDR5
GPU: AMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OS: Microsoft Windows 11 Home 10.0.26200
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 42.3
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.6
First chunk latency Delay before the first streamed chunk arrives from runtime: 718 ms
Time to first token How fast the model starts responding — lower is better: 718 ms
Load time Time to load the model into memory before inference: 28.5 s
Memory usage RAM consumed during inference — percentage of total system memory: 25.8 GB (83%)
Total tokens Total number of tokens generated across all benchmark prompts: 871

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

8/30

Quality

Reasoning

16/20

Coding

18/20

Instruction following

15/20

Structured output

15/15

Math

14/15

Multilingual

10/10

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: 1b4a0e78c5e1d1e066e9c37fd7c5116f6e9dfddcd49b53832f55b8c2dd083340

Interpretation

Hardware fit: 78/100. Overall suitability: EXCELLENT (Global 85/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Bench Environment

Power: AC Swap delta: +0.1 GB CPU load: avg 39% (peak 51%)

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