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 )

qwen3:0.6b

OLLAMA GGUF

qwen3 · 751.63M · Q4_K_M

Good

Apr 29, 2026 · Intel Core™ i5-8350U

Global Score
90 vs 61
Hardware Fit
96 vs 85
Quality Score
88 vs 51

Hardware

Kimi-48B:48B qwen3:0.6b
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLLENOVO 20L7CTO1WW
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Intel Core™ i5-8350U
Cores208
RAM55 GB23 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUKaby Lake-R GT2 [UHD Graphics 620]
OSMicrosoft Windows 11 Pro 10.0.28000Fedora Linux 43
Archarm64x64
Power Modebalancedlow-power

Performance

Kimi-48B:48B qwen3:0.6b
Tokens/sec62.727.0
First chunk397 ms597 ms
TTFT397 ms8.7 s
Load time16.8 s1.8 s
Memory usage25.5 GB0.9 GB
Memory %47%4%

HW Fit Score Breakdown

Kimi-48B:48B

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

qwen3:0.6b

Speed
50/50
TTFT
5/20
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

qwen3:0.6b

Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate
View Kimi-48B:48B details | View qwen3:0.6b 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