Back to leaderboard

qwen3-vl:30b

OLLAMA GGUF

qwen3vlmoe · 31.1B · Q4_K_M

Excellent

Mar 5, 2026 · Intel Core™ Ultra 9 285K

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 )

Global Score
80 vs 90
Hardware Fit
98 vs 96
Quality Score
72 vs 88

Hardware

qwen3-vl:30b Kimi-48B:48B
MachineASUSHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUIntel Core™ Ultra 9 285KNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores2420
RAM47 GB55 GB
GPUNVIDIA GeForce RTX 5090, Intel(R) GraphicsNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 Pro 10.0.28000
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3-vl:30b Kimi-48B:48B
Tokens/sec208.962.7
First chunk102 ms397 ms
TTFT684 ms397 ms
Load time0.1 s16.8 s
Memory usage22.0 GB25.5 GB
Memory %47%47%

HW Fit Score Breakdown

qwen3-vl:30b

Speed
50/50
TTFT
20/20
Memory
28/30

Kimi-48B:48B

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

Quality

qwen3-vl:30b

Reasoning
14/20
Coding
6/20
Instruction
17/20
Structured
12/15
Math
13/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

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

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