Back to leaderboard

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Excellent

Jun 13, 2026 · AMD Ryzen 9 3900X 12-Core Processor

gemma4:12b

OLLAMA GGUF

gemma4 · 11.9B · Q4_K_M

Not Rec.

Aug 22, 2026 · Apple M1 Pro

Global Score
82 vs 63
Hardware Fit
90 vs 62
Quality Score
79 vs 63

Hardware

qwen3:14b gemma4:12b
MachineMicro-Star International Co., Ltd. MS-7C37MacBook Pro
CPUAMD Ryzen 9 3900X 12-Core ProcessorApple M1 Pro
Cores2410
RAM64 GB16 GB
GPUGameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080Apple M1 Pro
OSMicrosoft Windows 11 专业版 10.0.26200macOS 26.6.2
Archx64arm64
Power Modebalancedbalanced

Performance

qwen3:14b gemma4:12b
Tokens/sec74.415.3
First chunk324 ms1142 ms
TTFT2.6 s30.0 s
Load time5.1 s5.4 s
Memory usage9.0 GB7.6 GB
Memory %14%47%

HW Fit Score Breakdown

qwen3:14b

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

gemma4:12b

Speed
36/50
TTFT
0/20
Memory
26/30

Quality

qwen3:14b

Reasoning
18/20
Coding
11/20
Instruction
17/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

gemma4:12b

Reasoning
10/20
Coding
10/20
Instruction
9/20
Structured
14/15
Math
10/15
Multilingual
10/10
Reasoning: Weak Coding: Adequate Instruction Following: Weak Structured Output: Strong Math: Adequate 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