Back to leaderboard

qwen3-coder:30b-a3b-q4_K_M

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Marginal

Jun 18, 2026 · Intel Core™ Ultra 9 285HX

gemma4:12b-it-qat

OLLAMA GGUF

gemma4 · 11.9B · Q4_0

Excellent

Jun 25, 2026 · Apple M4 Pro

Global Score
52 vs 88
Hardware Fit
69 vs 86
Quality Score
45 vs 89

Hardware

qwen3-coder:30b-a3… gemma4:12b-it-qat
MachineMicro-Star International Co., Ltd. Titan 18 HX AI A2XWJGMac mini
CPUIntel Core™ Ultra 9 285HXApple M4 Pro
Cores2412
RAM63 GB24 GB
GPUIntel(R) Graphics, NVIDIA GeForce RTX 5090 Laptop GPUApple M4 Pro
OSMicrosoft Windows 11 Home Single Language 10.0.26200macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3-coder:30b-a3… gemma4:12b-it-qat
Tokens/sec29.430.0
First chunk593 ms686 ms
TTFT593 ms7.1 s
Load time14.2 s5.4 s
Memory usage42.6 GB7.1 GB
Memory %67%30%

HW Fit Score Breakdown

qwen3-coder:30b-a3b-q4_…

Speed
33/50
TTFT
20/20
Memory
16/30

gemma4:12b-it-qat

Speed
50/50
TTFT
6/20
Memory
30/30

Quality

qwen3-coder:30b-a3b-q4_…

Reasoning
16/20
Coding
18/20
Instruction
0/20
Structured
0/15
Math
11/15
Multilingual
0/10
Reasoning: Strong Coding: Strong Instruction Following: Poor Structured Output: Poor Math: Strong Multilingual: Poor

gemma4:12b-it-qat

Reasoning
18/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate 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