Mlfoundations GGUF models

212 GGUF models in the Mlfoundations family, quantized by 7 uploaders. Sizes run from 1.24B to 32.8B parameters. The longest trained context is 128K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
ML
mlfoundations dev stackoverflow 5000tasks 0p
Mlfoundations · RichardErkhov
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev stackoverflow 5000tasks 1p
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev stackoverflow 10000tasks 0p
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev oh teknium scaling down ratiocontrolled 1.0
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev stackoverflow 10000tasks 1p
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev stackoverflow 5000tasks .75p
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev oh teknium scaling down ratiocontrolled 0.6
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev oh v1.3 camel chemistry x.5
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev OH original wo caseus custom
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev stackoverflow 5000tasks .25p
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev OH DCFT V3 wo unreplicated
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev oh teknium scaling down random 0.5
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev oh v1 2 only evol instruct
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev OH original wo evol instruct 140k
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev OH DCFT V3 wo collective cognition
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev oh v1.3 unnatural instructions x.125
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev.Bespoke Stratos 17k oldconfigs fast
Mlfoundations · csabakecskemeti
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
ML
mlfoundations dev oh teknium scaling down ratiocontrolled 0.3
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev oh v1.3 unnatural instructions x4
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev oh v1 2 only unnatural instructions
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev oh v1.3 opengpt x2
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev oh teknium scaling down ratiocontrolled 0.9
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev oh v1.3 evol instruct x2
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev oh v1.3 camel biology x.5
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev oh teknium scaling down random 1.0
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev oh v1.3 unnatural instructions x.5
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev oh dcft v3 sharegpt format sedrick
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev webinstruct v1 beta stage 3 shareGPT format
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev oh dcft v1.2 no curation gpt 4o mini wo metamath
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
ML
mlfoundations dev oh v3 1 only evol instruct 70k
Mlfoundations · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF

About the Mlfoundations GGUF models

Mlfoundations is represented on ggufmodels.com by 212 GGUF models, quantized by 7 uploaders on Hugging Face. The most downloaded are mlfoundations dev stackoverflow 5000tasks 0p, mlfoundations dev stackoverflow 5000tasks 1p and mlfoundations dev stackoverflow 10000tasks 0p. Parameter counts run from 1.24B to 32.8B, and the longest trained context window is 128K tokens.

A Q4_K_M file of a Mlfoundations model is between 0.0 to 4.9 GB, which is the quant most people start with. Most files come from RichardErkhov (179), tensorblock (24) and DevQuasar-11 (4). The quants you will meet most often are Q2_K (212), Q3_K_S (186), IQ3_XS (178) and IQ3_S (178), where the number is how many models offer that quant.

Frequently asked questions

Which Mlfoundations GGUF should I download?

The most downloaded Mlfoundations GGUF here is mlfoundations dev stackoverflow 5000tasks 0p. 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 Mlfoundations model need?

Q4_K_M files of Mlfoundations models on this site range from 0.0 to 4.9 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 Mlfoundations GGUF files come from?

The most common quantizers here are RichardErkhov, tensorblock and DevQuasar-11. 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