lmstudio-community/gemma-4-12b-it-qat
LM-STUDIO GGUFgemma4 · 12B · Q4_0
Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H
gemma4:12b-mlx
OLLAMA GGUFJul 4, 2026 · Apple M2 Pro
Global Score
75 vs 84
Hardware Fit
48 vs 82
Quality Score
86 vs 85
Hardware
lmstudio-community… gemma4:12b-mlx
MachineDocker ContainerMacBook Pro
CPUIntel Gen Intel® Core™ i9-11900HApple M2 Pro
Cores1610
RAM15 GB16 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M2 Pro
OSUbuntu 26.04 LTSmacOS 26.5
Archx64arm64
Power Modeperformancebalanced
Performance
lmstudio-community… gemma4:12b-mlx
Tokens/sec5.827.2
First chunk101 ms732 ms
TTFT5.3 s8.1 s
Load time11.0 s3.5 s
Memory usage0.6 GB7.1 GB
Memory %4%44%
HW Fit Score Breakdown
lmstudio-community/gemm…
Speed
10/50
TTFT
8/20
Memory
30/30
gemma4:12b-mlx
Speed
50/50
TTFT
6/20
Memory
26/30
Quality
lmstudio-community/gemm…
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
gemma4:12b-mlx
Reasoning
16/20
Coding
17/20
Instruction
13/20
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$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest