Back to leaderboard

qwen3.5:4b-mlx

OLLAMA GGUF

nvfp4

Marginal

Aug 24, 2026 · Apple M2

google/gemma-4-12b-it-qat

LM-STUDIO GGUF

gemma4 · 12B · Q4_0

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
53 vs 74
Hardware Fit
82 vs 46
Quality Score
41 vs 86

Hardware

qwen3.5:4b-mlx google/gemma-4-12b…
MachineMac miniDocker Container
CPUApple M2Intel Gen Intel® Core™ i9-11900H
Cores816
RAM8 GB15 GB
GPUApple M2TigerLake-H GT1 [UHD Graphics]
OSmacOS 26.5.2Ubuntu 26.04 LTS
Archarm64x64
Power Modebalancedperformance

Performance

qwen3.5:4b-mlx google/gemma-4-12b…
Tokens/sec24.75.0
First chunk302 ms64 ms
TTFT7.4 s5.5 s
Load time3.2 s9.5 s
Memory usage3.8 GB0.0 GB
Memory %47%0%

HW Fit Score Breakdown

qwen3.5:4b-mlx

Speed
50/50
TTFT
6/20
Memory
26/30

google/gemma-4-12b-it-qat

Speed
9/50
TTFT
7/20
Memory
30/30

Quality

qwen3.5:4b-mlx

Reasoning
13/20
Coding
2/20
Instruction
4/20
Structured
4/15
Math
10/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Poor Structured Output: Weak Math: Adequate Multilingual: Strong

google/gemma-4-12b-it-qat

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen3.5:4b-mlx details | View google/gemma-4-12b… 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