llmrun
GoogleGemma 3

Gemma 3 12B Pt — Hardware Requirements & GPU Compatibility

Vision

Gemma 3 12B PT is Google's roughly 12-billion-parameter pretrained checkpoint in the Gemma 3 family, built on a vision-language architecture that accepts both text and images. The PT suffix marks the base model: it lacks instruction tuning and doesn't handle chat prompts well, so it serves as a starting point for fine-tuning or research instead of direct use as an assistant. Hugging Face lists this version as image-text-to-text. At this size it fits on a single consumer GPU once quantized, while the instruction-tuned variant remains the standard choice for conversation. It supports a 128K-token context window. Distribution follows the Gemma Terms of Use, and access requires acknowledging the license on Hugging Face. Released in March 2025, it falls between the 4B and 27B models within the Gemma 3 lineup.

12.2B params · denseGemma Terms42.4K downloads97 likes1.3K quant downloads
S

Runs great on a 24 GB GPU

Runs from8 GB IQ2_M · 16KBest on24 GB Q4_K_M · ~82 tok/s · 32KMacs from16 GB Q4_K_M · ~17 tok/s

Gemma Terms

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

Run Gemma 3 12B Pt

One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.

Recommended

Ollama
one command · needs Ollama installed
$ollama run hf.co/mradermacher/gemma-3-12b-pt-i1-GGUF:Q4_K_M

Q4_K_M fits fully on the RTX 4090 · 13.1 GB free · 16K context

Download: gemma-3-12b-pt.i1-Q4_K_M.gguf7.30 GBmradermacher

install, OS, other quants

Ways to runOther ways

each opens step-by-step

Run in cloud

Your own private copy · Q4_K_M · 24 GB GPU

  • The easiest way to try this model
  • Running in a few minutes, easy setup
  • Chat right here or connect any app

$5+ bonus for new users

How Much VRAM Does Gemma 3 12B Pt Need?

Select a quantization level; the listed hardware adheres to it.

QuantizationVRAM+32KOn RTX 4090 (reference)
5.7 GB11.9 GB2-bit · K-quant — 2-bit quantization with K-quant improvementsFits: 32K context · ~115 tok/s
5.9 GB12.1 GB3-bit small — 3-bit small quantizationFits: 32K context · ~112 tok/s
6.5 GB12.7 GB3-bit medium — 3-bit medium quantizationFits: 32K context · ~100 tok/s
6.7 GB12.9 GB4-bit · legacy — 4-bit legacy quantizationFits: 32K context · ~98 tok/s
8.0 GB14.2 GB4-bit medium — 4-bit medium quantization — most popular sweet spotFits: 32K context · ~82 tok/s
9.6 GB15.7 GB5-bit medium — 5-bit medium quantization — good quality/size tradeoffFits: 32K context · ~69 tok/s
11.1 GB17.3 GB6-bit, very good — 6-bit quantization, very good qualityFits: 32K context · ~59 tok/s
13.4 GB19.6 GB8-bit, near-lossless — 8-bit quantization, near-losslessFits: 32K context · ~49 tok/s
est.calculated, no published file yet

Selected Q4_K_M

4-bit medium quantization

10.9GBat 16K context

Weights
7.3 GB
KV cache
3.3 GB
Overhead
0.3 GB

Fits RTX 4090 (reference) · 13.1 GB free · ~82 tok/s

≥50 tok/s needs ≥618 GB/s · RTX 5090 ~145, M5 Ultra ~107

Which Hardware Can Run Gemma 3 12B Pt?

Q4_K_M · 8.0 GB

Gemma 3 12B Pt (Q4_K_M) requires 8.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 11+ GB is recommended. 51 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 3080 Ti. 171 devices with unified memory can run Gemma 3 12B Pt, including Mac Studio M5 Ultra (256 GB), Mac Studio M5 Ultra (512 GB), Snapdragon X Plus (8-core) Copilot+ PC.

By VRAM tier · typical GPUs and Macs at Q4_K_M
8 GB · RTX 4060IQ2_M · 7.4 GB · ~39 tok/s · 16K8 GB tier →
12 GB · RTX 3060 12GBQ4_K_M · 10.9 GB · ~29 tok/s · 16K12 GB tier →
16 GB · RTX 5060 Ti 16GBQ4_K_M · 10.9 GB · ~36 tok/s · 32K16 GB tier →
24 GB · RTX 4090referenceQ4_K_M · 10.9 GB · ~82 tok/s · 32K24 GB tier →
Mac 32 GB · Mac Mini M4Q4_K_M · 10.9 GB · ~10 tok/s · 32KMacs →
Mac 64 GB · Mac Studio M4 MaxQ4_K_M · 10.9 GB · ~48 tok/s · 32KMacs →

Alternatives to Gemma 3 12B Pt

Gemma 3 family · 20 models →

Similar models

6
ModelScoreVRAMtok/sWhy it is similar
Mistral Nemo Base 2407Mistral AI—11 GB~81same size
Baichuan2 13B Basebaichuan-inc—11.5 GB~76same size
Llama 2 13B Chat HFMeta—11.5 GB~76same size
Vicuna 13B V1.3LMSYS—8.6 GB~76same size
NVIDIA Nemotron Nano 12B v2NVIDIA—11 GB~81same size
Midm 2.0 Base InstructK-intelligence—10.5 GB~86same size
Fine-tunes & variants(2)

Specifications

Publisher
Google
Family
Gemma 3
Parameters
12.2B
Release Date
2025-03-01
License
Gemma Terms

Frequently Asked Questions

How much VRAM does Gemma 3 12B Pt need?

Gemma 3 12B Pt requires 8.0 GB of VRAM at Q4_K_M, or 26.8 GB at BF16.

VRAM = Weights + KV Cache + Overhead

Weights = 12.2B × 4.8 bits ÷ 8 = 7.3 GB

KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)

Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.

VRAM usage by quantization

8.0 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 4090 run Gemma 3 12B Pt?

Yes, at Q8_0 (13.4 GB) or lower. Higher quantizations like BF16 (26.8 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.

What's the best quantization for Gemma 3 12B Pt?

For Gemma 3 12B Pt, Q4_K_M (8.0 GB) offers the best balance of quality and VRAM usage. Q5_K_S (9.2 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 3.7 GB.

VRAM requirement by quantization

IQ2_XXS
3.7 GB
IQ3_XS
5.5 GB
Q4_0
6.7 GB
IQ4_NL
7.5 GB
Q4_K_M ★
8.0 GB
BF16
26.8 GB

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run Gemma 3 12B Pt on a Mac?

Yes — Mac Mini M2 Pro (16 GB) and 145 other Macs can run Gemma 3 12B Pt. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 8.0 GB of usable unified memory (RAM minus macOS overhead).

Can I run Gemma 3 12B Pt locally?

Yes — Gemma 3 12B Pt can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Gemma 3 12B Pt?

At Q4_K_M, Gemma 3 12B Pt can reach ~597 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~82 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = (bandwidth GB/s ÷ model GB) × efficiency

Example: NVIDIA B200 → 8000 ÷ 8.04 × 0.65 = ~647 tok/s

Estimated speed at Q4_K_M (8.0 GB)

~647 tok/s
~82 tok/s
~647 tok/s
~597 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of Gemma 3 12B Pt?

At Q4_K_M, the download is about 7.31 GB. The full-precision BF16 version is 24.37 GB. The smallest option (IQ2_XXS) is 3.35 GB.

Which GPUs can run Gemma 3 12B Pt?

51 consumer GPUs can run Gemma 3 12B Pt at Q4_K_M. Top options include AMD Radeon RX 6800, AMD Radeon RX 6800 XT, AMD Radeon RX 6900 XT, AMD Radeon RX 6700 XT. 30 GPUs have plenty of headroom for comfortable inference.

Which devices can run Gemma 3 12B Pt?

171 devices with unified memory can run Gemma 3 12B Pt at Q4_K_M (8.0 GB), including AMD Ryzen 7 8845HS (Hawk Point) Laptop, AMD Ryzen AI 7 350 (Krackan Point) Laptop, AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10. Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.