Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Excellent

Jul 7, 2026 · Cortex-X925

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
83 vs 90
Hardware Fit
60 vs 96
Quality Score
93 vs 88

Hardware

gemma4:31b Kimi-48B:48B
MachineASUSTeK COMPUTER INC. GX10HP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUCortex-X925NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores2020
RAM122 GB55 GB
GPUDevice 2e12NVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSUbuntu 24.04.4 LTSMicrosoft Windows 11 Pro 10.0.28000
Archarm64arm64
Power Modeperformancebalanced

Performance

gemma4:31b Kimi-48B:48B
Tokens/sec10.962.7
First chunk681 ms397 ms
TTFT681 ms397 ms
Load time16.6 s16.8 s
Memory usage21.4 GB25.5 GB
Memory %18%47%

HW Fit Score Breakdown

gemma4:31b

Speed
10/50
TTFT
20/20
Memory
30/30

Kimi-48B:48B

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

Quality

gemma4:31b

Reasoning
19/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong 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