Back to leaderboard

Qwen3-Coder-30B:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Aug 18, 2026 · Intel Core™ i7-14700F

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
91 vs 90
Hardware Fit
100 vs 96
Quality Score
87 vs 88

Hardware

Qwen3-Coder-30B:30b Kimi-48B:48B
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUIntel Core™ i7-14700FNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores2820
RAM128 GB55 GB
GPUNVIDIA GeForce RTX 5080NVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows 11 Pro 10.0.28000
Archx64arm64
Power Modebalancedbalanced

Performance

Qwen3-Coder-30B:30b Kimi-48B:48B
Tokens/sec74.062.7
First chunk381 ms397 ms
TTFT381 ms397 ms
Load time15.3 s16.8 s
Memory usage17.9 GB25.5 GB
Memory %14%47%

HW Fit Score Breakdown

Qwen3-Coder-30B:30b

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

Kimi-48B:48B

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

Quality

Qwen3-Coder-30B:30b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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