Back to leaderboard

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 )

llama3.2:1b

OLLAMA GGUF

llama · 1.2B · Q8_0

Good

Mar 5, 2026 · AMD Ryzen 9 8945HS

Global Score
90 vs 62
Hardware Fit
96 vs 91
Quality Score
88 vs 50

Hardware

Kimi-48B:48B llama3.2:1b
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLASUSTeK COMPUTER INC. ROG Zephyrus G14 GA403UV_GA403UV
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )AMD Ryzen 9 8945HS
Cores2016
RAM55 GB15 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUNVIDIA GeForce RTX 4060 Laptop GPU, AMD Radeon 780M Graphics
OSMicrosoft Windows 11 Pro 10.0.28000Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

Kimi-48B:48B llama3.2:1b
Tokens/sec62.7170.2
First chunk397 ms142 ms
TTFT397 ms142 ms
Load time16.8 s3.2 s
Memory usage25.5 GB1.6 GB
Memory %47%11%

HW Fit Score Breakdown

Kimi-48B:48B

Speed
50/50
TTFT
20/20
Memory
26/30

llama3.2:1b

Speed
50/50
TTFT
20/20
Memory
21/30

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

llama3.2:1b

Reasoning
4/20
Coding
13/20
Instruction
14/20
Structured
13/15
Math
0/15
Multilingual
6/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Adequate

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