FL

flux imatrix

FluxGGUF by EviationUpdated 2025-03-25
Download on Hugging Face
Parameters11.9B
Context—
Layers—
Architectureflux
Smallest quant2.4 GB
Quick answer

flux imatrix needs about 8.0 GB of memory at Q4_K_M (a 6.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 74 quants, from 2.4 GB (IQ1_S) to 12.3 GB (Q8_0).

Flux Imatrix – 11.9B parameter image generation model

Flux Imatrix is a 11.9B parameter model in the Flux family, based on black-forest-labs/FLUX.1-dev. It supports image generation with multiple image inputs and is available in several GGUF quantizations.

Good at

  • Multi‑image generation
  • 512x512 and 768x768 support
  • Low‑latency inference with small quants

Limits

  • No vision support beyond images
  • Large memory requirement for high‑bit quants
  • License is other, use at own discretion

Best for

  • Creating composite images
  • Rapid prototyping of image prompts
  • Running on mid‑range GPUs

Who it’s for. Developers and researchers needing a flexible image generation model that can handle multiple image inputs. Suitable for those who can manage the memory footprint and are comfortable with the provided quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.4 GB 3.2 GB
Fits Get file →
IQ1_S2.4 GB 3.2 GB
Fits Get file →
IQ1_S2.4 GB 3.2 GB
Fits Get file →
TQ1_02.6 GB 3.4 GB
Fits Get file →
TQ1_02.6 GB 3.5 GB
Fits Get file →
IQ1_M2.7 GB 3.5 GB
Fits Get file →
IQ1_M2.7 GB 3.5 GB
Fits Get file →
IQ2_XXS3.1 GB 4.0 GB
Fits Get file →
TQ2_03.1 GB 4.0 GB
Fits Get file →
IQ2_XXS3.2 GB 4.1 GB
Fits Get file →
IQ2_XXS3.2 GB 4.1 GB
Fits Get file →
TQ2_03.2 GB 4.1 GB
Fits Get file →
IQ2_XS3.5 GB 4.4 GB
Fits Get file →
IQ2_S3.5 GB 4.4 GB
Fits Get file →
IQ2_S3.6 GB 4.5 GB
Fits Get file →
IQ2_XS3.6 GB 4.5 GB
Fits Get file →
IQ2_S3.6 GB 4.5 GB
Fits Get file →
IQ2_XS3.6 GB 4.5 GB
Fits Get file →
IQ2_M3.8 GB 4.8 GB
Fits Get file →
IQ2_M3.9 GB 4.9 GB
Fits Get file →
IQ2_M3.9 GB 4.9 GB
Fits Get file →
Q2_K_S4.0 GB 5.0 GB
Fits Get file →
Q2_K_S4.0 GB 5.0 GB
Fits Get file →
Q2_K4.0 GB 5.0 GB
Fits Get file →
Q2_K_S4.0 GB 5.0 GB
Fits Get file →
Q2_K4.0 GB 5.0 GB
Fits Get file →
IQ3_XXS4.6 GB 5.6 GB
Fits Get file →
IQ3_XXS4.7 GB 5.7 GB
Fits Get file →
IQ3_XXS4.7 GB 5.7 GB
Fits Get file →
IQ3_XS5.0 GB 6.2 GB
Fits Get file →
Q3_K_S5.1 GB 6.2 GB
Fits Get file →
IQ3_S5.1 GB 6.2 GB
Fits Get file →
Q3_K_M5.1 GB 6.2 GB
Fits Get file →
IQ3_M5.1 GB 6.3 GB
Fits Get file →
Q3_K_L5.2 GB 6.3 GB
Fits Get file →
IQ3_XS5.2 GB 6.3 GB
Fits Get file →
Q3_K_S5.2 GB 6.3 GB
Fits Get file →
IQ3_M5.2 GB 6.3 GB
Fits Get file →
IQ3_S5.2 GB 6.3 GB
Fits Get file →
IQ3_XS5.2 GB 6.3 GB
Fits Get file →
Q3_K_S5.2 GB 6.3 GB
Fits Get file →
Q3_K_L5.4 GB 6.5 GB
Fits Get file →
Q3_K_M5.4 GB 6.5 GB
Fits Get file →
IQ4_XS6.3 GB 7.6 GB
Tight Get file →
IQ4_XS6.4 GB 7.7 GB
Tight Get file →
IQ4_XS6.4 GB 7.7 GB
Tight Get file →
Q4_K_S6.7 GB 8.0 GB
Tight Get file →
IQ4_NL6.7 GB 8.0 GB
Tight Get file →
Q4_K_M6.7 GB 8.0 GB
Tight Get file →
Q4_06.7 GB 8.0 GB
Too big Get file →
IQ4_NL6.8 GB 8.1 GB
Too big Get file →
Q4_06.8 GB 8.1 GB
Too big Get file →
Q4_K_S6.8 GB 8.1 GB
Too big Get file →
IQ4_NL6.8 GB 8.1 GB
Too big Get file →
Q4_06.8 GB 8.1 GB
Too big Get file →
Q4_K_S6.8 GB 8.1 GB
Too big Get file →
Q4_06.8 GB 8.1 GB
Too big Get file →
Q4_K_M6.9 GB 8.3 GB
Too big Get file →
Q4_17.5 GB 8.9 GB
Too big Get file →
Q4_17.5 GB 8.9 GB
Too big Get file →
Q4_17.5 GB 9.0 GB
Too big Get file →
Q5_K_S8.3 GB 9.7 GB
Too big Get file →
Q5_08.3 GB 9.8 GB
Too big Get file →
Q5_08.3 GB 9.8 GB
Too big Get file →
Q5_K_S8.3 GB 9.8 GB
Too big Get file →
Q5_K_S8.3 GB 9.8 GB
Too big Get file →
Q5_K_M8.3 GB 9.8 GB
Too big Get file →
Q5_K8.4 GB 9.9 GB
Too big Get file →
Q5_19.0 GB 10.6 GB
Too big Get file →
Q5_19.0 GB 10.6 GB
Too big Get file →
Q6_K9.8 GB 11.5 GB
Too big Get file →
Q6_K9.8 GB 11.5 GB
Too big Get file →
Q6_K9.8 GB 11.5 GB
Too big Get file →
Q8_012.3 GB 14.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.41 GB file, ~3.2 GB memory) or TQ1_0 (2.63 GB file, ~3.4 GB memory). For 12 GB VRAM, IQ2_XXS (3.1 GB file, ~4 GB memory) or TQ2_0 (3.12 GB file, ~4 GB memory) are suitable. Higher‑bit quants require 16 GB or more.

What GPU do you need for flux imatrix?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is TQ2_0 (3.1 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ3_XXS (4.7 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_0 (6.7 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (12.3 GB file, about 14.3 GB in use).

Which flux imatrix quant should you choose?

Q4_K_M is the usual starting point for flux imatrix: it balances file size and quality well. Here it is a 6.7 GB file.

The Q8_0 file is 12.3 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ1_S at 2.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureflux
Parameters11.9B

Source

Quantized byEviation
FamilyFlux
Licenseother
Downloads (HF)6,112
Last updated2025-03-25

Frequently asked questions about flux imatrix

How much VRAM does flux imatrix need?

About 8.0 GB at Q4_K_M with an 8K context window. That is the 6.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run flux imatrix on an 8 GB GPU?

Yes, with Q4_0: the 6.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of flux imatrix GGUF?

It depends on the quant: IQ1_S is 2.4 GB, IQ1_S is 2.4 GB, IQ1_S is 2.4 GB, TQ1_0 is 2.6 GB, TQ1_0 is 2.6 GB, IQ1_M is 2.7 GB and 68 more.

Where can I download flux imatrix GGUF?

The files are on Hugging Face in the Eviation/flux-imatrix repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does flux imatrix use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Flux Imatrix on 8 GB VRAM?

Yes, with IQ1_S or TQ1_0 quantizations, which use about 3.2 GB of VRAM at 8k context.

What is the smallest quant available?

IQ1_S is the smallest, 2.41 GB file size and ~3.2 GB memory at 8k context.

Does Flux Imatrix support text prompts?

The model focuses on image generation; text prompt support is limited and not highlighted in the provided data.

Other GGUFs of FLUX.1-dev

Similar models

Browse all →

More from Eviation

All by Eviation →

More Flux models

All Flux →

Other medium models

All medium models →