Back to leaderboard

google/gemma-4-12b-qat

LM-STUDIO GGUF

gemma4 · 12B · Q4_0

Excellent

Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor

qwen3.5-2b-mlx

LM-STUDIO MLX

qwen3_5 · 2B · 4bit

Good

Mar 6, 2026 · Apple M4 Pro

Global Score
92 vs 65
Hardware Fit
100 vs 88
Quality Score
89 vs 55

Hardware

google/gemma-4-12b… qwen3.5-2b-mlx
MachineMicro-Star International Co., Ltd. MS-7E51Mac mini
CPUAMD Ryzen 7 9700X 8-Core ProcessorApple M4 Pro
Cores1614
RAM31 GB64 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 15.7.4
Archx64arm64
Power Modebalancedbalanced

Performance

google/gemma-4-12b… qwen3.5-2b-mlx
Tokens/sec90.748.9
First chunk26 ms4208 ms
TTFT127 ms4.2 s
Load timeN/AN/A
Memory usage6.7 GB1.6 GB
Memory %21%3%

HW Fit Score Breakdown

google/gemma-4-12b-qat

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

qwen3.5-2b-mlx

Speed
50/50
TTFT
8/20
Memory
30/30

Quality

google/gemma-4-12b-qat

Reasoning
17/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3.5-2b-mlx

Reasoning
10/20
Coding
7/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor Multilingual: Strong
View google/gemma-4-12b… details | View qwen3.5-2b-mlx details

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