Back to leaderboard

Qwen3-30B:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )

gemma4:12b

OLLAMA GGUF

gemma4 · 11.9B · Q4_K_M

Excellent

Jul 4, 2026 · Apple M2 Pro

Global Score
91 vs 89
Hardware Fit
98 vs 88
Quality Score
88 vs 89

Hardware

Qwen3-30B:30b gemma4:12b
MachineHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXMLMacBook Pro
CPUNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )Apple M2 Pro
Cores2010
RAM55 GB16 GB
GPUNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPUApple M2 Pro
OSMicrosoft Windows 11 Pro 10.0.28000macOS 26.5
Archarm64arm64
Power Modebalancedbalanced

Performance

Qwen3-30B:30b gemma4:12b
Tokens/sec80.518.4
First chunk158 ms758 ms
TTFT158 ms758 ms
Load time21.8 s0.3 s
Memory usage20.3 GB7.5 GB
Memory %37%47%

HW Fit Score Breakdown

Qwen3-30B:30b

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

gemma4:12b

Speed
42/50
TTFT
20/20
Memory
26/30

Quality

Qwen3-30B:30b

Reasoning
16/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

gemma4:12b

Reasoning
17/20
Coding
18/20
Instruction
17/20
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