Back to leaderboard

qwen3-coder:latest

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Good

May 24, 2026 · Intel Gen Intel® Core™ i7-1355U

gemma4:12b

OLLAMA GGUF

gemma4 · 11.9B · Q4_K_M

Excellent

Jul 4, 2026 · Apple M2 Pro

Global Score
76 vs 89
Hardware Fit
51 vs 88
Quality Score
87 vs 89

Hardware

qwen3-coder:latest gemma4:12b
MachineDell Inc. Inspiron 15 3530MacBook Pro
CPUIntel Gen Intel® Core™ i7-1355UApple M2 Pro
Cores1210
RAM31 GB16 GB
GPURaptor Lake-P [Iris Xe Graphics]Apple M2 Pro
OScachyos rollingmacOS 26.5
Archx64arm64
Power Modelow-powerbalanced

Performance

qwen3-coder:latest gemma4:12b
Tokens/sec7.618.5
First chunk2037 ms752 ms
TTFT2.0 s752 ms
Load time8.7 s6.1 s
Memory usage18.9 GB7.5 GB
Memory %61%47%

HW Fit Score Breakdown

qwen3-coder:latest

Speed
13/50
TTFT
18/20
Memory
20/30

gemma4:12b

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

Quality

qwen3-coder:latest

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

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