Back to leaderboard

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

LM-STUDIO GGUF

gemma4 · 12B · Q4_0

Good

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

phi-3.5-mini-instruct

LM-STUDIO MLX

phi3 · 4bit

Marginal

Mar 4, 2026 · Apple M4

Global Score
74 vs 55
Hardware Fit
46 vs 100
Quality Score
86 vs 36

Hardware

google/gemma-4-12b… phi-3.5-mini-instr…
MachineDocker ContainerMacBook Air
CPUIntel Gen Intel® Core™ i9-11900HApple M4
Cores1610
RAM15 GB32 GB
GPUTigerLake-H GT1 [UHD Graphics]Apple M4
OSUbuntu 26.04 LTSmacOS 26.3
Archx64arm64
Power Modeperformancebalanced

Performance

google/gemma-4-12b… phi-3.5-mini-instr…
Tokens/sec5.043.4
First chunk64 ms359 ms
TTFT5.5 s359 ms
Load time9.5 sN/A
Memory usage0.0 GB2.0 GB
Memory %0%6%

HW Fit Score Breakdown

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

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

phi-3.5-mini-instruct

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

Quality

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

phi-3.5-mini-instruct

Reasoning
11/20
Coding
4/20
Instruction
7/20
Structured
1/15
Math
7/15
Multilingual
6/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Weak Multilingual: Adequate
View google/gemma-4-12b… details | View phi-3.5-mini-instr… 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