Stable GGUF models

120 GGUF models in the Stable family, quantized by 55 uploaders. Sizes run from 84M to 16.4B parameters. The longest trained context is 32K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
ST
stable diffusion v1 5
Stable · second-state
Params1.07B
Context—
Smallest1.6 GB
GGUF
ST
stable diffusion 3.5 large
Stable · second-state
Params695M
Context—
Smallest0.7 GB
GGUF
ST
stable diffusion 3.5 medium
Stable · second-state
Params695M
Context—
Smallest0.1 GB
GGUF
ST
sd3.5 large
Stable · calcuis
Params8.15B
Context—
Smallest4.8 GB
GGUF
ST
stable diffusion 3.5 large
Stable · city96
Params8.15B
Context—
Smallest4.8 GB
GGUF
ST
stable diffusion xl base 1.0
Stable · gpustack
Params3.47B
Context—
Smallest3.9 GB
GGUF
ST
stable-audio-3-medium SAME-L
Stable · thepatch
Params—
Context—
Q4_K_M0.6 GB
GGUF
ST
stable code 3b
Stable · stabilityai
Params2.8B
Context16K
Smallest2.0 GB
Coding
ST
stable diffusion v1 5
Stable · gpustack
Params1.07B
Context—
Smallest1.7 GB
GGUF
ST
sd3.5 medium
Stable · calcuis
Params2.47B
Context—
Q4_K_M1.8 GB
GGUF
ST
stable diffusion v1 5
Stable · kostakoff
Params1.07B
Context—
Smallest2.2 GB
GGUF
ST
stable-code-instruct-3b
Stable · mradermacher
Params2.8B
Context16K
Q4_K_M1.7 GB
Coding
ST
stable code 3b
Stable · TheBloke
Params2.8B
Context16K
Q4_K_M1.7 GB
Coding
ST
stable-code-3b
Stable · mradermacher
Params2.8B
Context16K
Q4_K_M1.7 GB
Coding
ST
stable diffusion 3.5 medium
Stable · city96
Params2.47B
Context—
Q4_K_M1.8 GB
GGUF
ST
stable code instruct 3b
Stable · QuantFactory
Params2.8B
Context16K
Q4_K_M1.7 GB
Coding
ST
stable-code-3b
Stable · mradermacher
Params2.8B
Context16K
Q4_K_M1.7 GB
Coding
ST
stable diffusion xl base 1.0
Stable · kostakoff
Params3.47B
Context—
Smallest2.7 GB
GGUF
ST
stable diffusion v2 1
Stable · gpustack
Params1.29B
Context—
Smallest2.2 GB
GGUF
ST
stable-code-instruct-3b
Stable · stabilityai
Params2.8B
Context16K
Q4_K_M1.7 GB
Coding
ST
stable diffusion 3.5 medium turbo
Stable · tensorart
Params2.47B
Context—
Q4_K_M1.8 GB
GGUF
ST
stable diffusion v2 1 turbo
Stable · gpustack
Params1.29B
Context—
Smallest2.2 GB
GGUF
ST
stable-code-instruct-3b
Stable · mradermacher
Params2.8B
Context16K
Q4_K_M1.7 GB
Coding
ST
stable-code-instruct-3b
Stable · lmstudio-community
Params2.8B
Context16K
Q4_K_M1.7 GB
Coding
ST
SDXL
Stable · HyperX-Sentience
Params2.57B
Context—
Smallest1.5 GB
GGUF
ST
stable diffusion 3.5 large turbo
Stable · city96
Params8.15B
Context—
Smallest4.8 GB
GGUF
ST
stable diffusion xl 1.0 turbo
Stable · gpustack
Params3.47B
Context—
Smallest3.9 GB
GGUF
ST
sd3.5 large
Stable · gguf-org
Params695M
Context—
Smallest0.2 GB
GGUF
ST
stable code 3b
Stable · QuantFactory
Params2.8B
Context16K
Q4_K_M1.7 GB
Coding
ST
stable diffusion xl inpainting 1.0
Stable · gpustack
Params3.47B
Context—
Smallest3.8 GB
GGUF

About the Stable GGUF models

Stable is represented on ggufmodels.com by 120 GGUF models, quantized by 55 uploaders on Hugging Face. The most downloaded are stable diffusion v1 5, stable diffusion 3.5 large and stable diffusion 3.5 medium. Parameter counts run from 84M to 16.4B, and the longest trained context window is 32K tokens.

A Q4_K_M file of a Stable model is between 0.1 to 7.9 GB, which is the quant most people start with. Most files come from gpustack (14), mradermacher (10) and thepatch (8). The quants you will meet most often are Q8_0 (88), Q4_0 (63), Q4_K_M (51) and Q4_1 (47), where the number is how many models offer that quant.

Frequently asked questions

Which Stable GGUF should I download?

The most downloaded Stable GGUF here is stable diffusion v1 5. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Stable model need?

Q4_K_M files of Stable models on this site range from 0.1 to 7.9 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Stable GGUF files come from?

The most common quantizers here are gpustack, mradermacher and thepatch. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing