OpenModelsHQ

gemma-3-12b-it-qat-q4_0-unquantized

LightricksVisionDenseGemma terms

gemma-3-12b-it-qat-q4_0-unquantized is an open-weight vision and language model from Lightricks with 12.2B parameters. At 4-bit it needs about 11.6 GB of memory, so the smallest current device that fits it is the GeForce RTX 5060 Ti 16GB.

Overview

Estimated memory at 4-bit
11.6GB

Includes room for an 8k context and runtime overhead. More context needs more memory.

Total parameters
12.2B
Dense
Context window
128K
131,072 tokens
Cheapest API, blended / 1M
No hosted API
Weights only

Key information

Lab
Lightricks
Released
4 Mar 2026
Parameters
12.2B
Type
Vision and language
Context
131,072 tokens
HF downloads, 30 days
19,356
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
gemma-3-12b-it-qat-q4_0-unquantized needs about 11.6 GB at 4-bit, 17.8 GB at 8-bit and 30.4 GB at 16-bit. At 4-bit it fits GeForce RTX 5060 Ti 16GB, GeForce RTX 5090, DGX Spark, Mac Studio M5 Ultra (256GB). Dashed lines are usable memory on each device; a model fits when its estimate stays within 90% of it. Log scale. 8k context.
Memory needed vs devices: data
Estimate or deviceMemory
Q411.6 GB
Q817.8 GB
BF1630.4 GB
RTX 5060 Ti 16 GB16 GB usable
RTX 5090 32 GB32 GB usable
DGX Spark 128 GB108.8 GB usable
Mac Studio M5 Ultra 256 GB192 GB usable

Single-device memory estimate. Pick a device to update the On your device column.

36 GB usable memory

FormatMemory neededOn your deviceExample hardware
4-bit (Q4)≈ 11.6 GBFits 32%GeForce RTX 5060 Ti 16GB16 GB memory
8-bit (Q8)≈ 17.8 GBFits 49%Arc Pro B6024 GB memory
16-bit (BF16)≈ 30.4 GBFits 84%L40S48 GB memory

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

No trusted MLX build found yet.

Check your Mac

With GGUF

No trusted GGUF build found yet.

Find compatible hardware

Through an API

No hosted API found.

More about this model

Frequently asked questions

How much memory does gemma-3-12b-it-qat-q4_0-unquantized need? At an 8k context, about 11.6 GB at 4-bit, 17.8 GB at 8-bit and 30.4 GB at 16-bit (BF16). A longer context needs more.

Can I run gemma-3-12b-it-qat-q4_0-unquantized on a Mac? The smallest current Mac that fits the 4-bit estimate of 11.6 GB is the Mac mini M5 Pro (24GB). We have not found a trusted MLX or GGUF build yet.

Does the full context fit? gemma-3-12b-it-qat-q4_0-unquantized supports up to 131,072 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? We did not find a hosted API for this model.

License in plain English

Gemma terms. These are Google's Gemma terms of use. They allow use and distribution with conditions, including a prohibited use policy. This summary is not legal advice.

Read Gemma terms

Read about this license

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources

Last updated . Sources:Hugging Face model card.