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 )

qwen3.5-35b-a3b-mtp

LM-STUDIO GGUF

qwen35moe · 35B · IQ3_XXS

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score

90 vs 77

Hardware Fit

96 vs 51

Quality Score

88 vs 88

Hardware

Kimi-48B:48B qwen3.5-35b-a3b-mtp

MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLDocker Container

CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Intel Gen Intel® Core™ i9-11900H

Cores2016

RAM55 GB15 GB

GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUTigerLake-H GT1 [UHD Graphics]

OSMicrosoft Windows 11 Pro 10.0.28000Ubuntu 26.04 LTS

Archarm64x64

Power Modebalancedperformance

Performance

Kimi-48B:48B qwen3.5-35b-a3b-mtp

Tokens/sec62.77.8

First chunk397 ms30 ms

TTFT397 ms5.6 s

Load time16.8 s32.5 s

Memory usage25.5 GB0.0 GB

Memory %47%0%

HW Fit Score Breakdown

Kimi-48B:48B

Speed

50/50

TTFT

20/20

Memory

26/30

qwen3.5-35b-a3b-mtp

Speed

14/50

TTFT

7/20

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

qwen3.5-35b-a3b-mtp

Reasoning

17/20

Coding

18/20

Instruction

17/20

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 qwen3.5-35b-a3b-mtp 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