Helpingai GGUF models

79 GGUF models in the Helpingai family, quantized by 14 uploaders. Sizes run from 110M to 17.5B parameters. The longest trained context is 1024K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
HE
HelpingAI-15B
Helpingai · mradermacher
Params15.3B
Context4K
Q4_K_M9.3 GB
GGUF
HE
HelpingAI-9B
Helpingai · mradermacher
Params8.83B
Context4K
Q4_K_M5.3 GB
GGUF
HE
HelpingAI 3B hindi i1
Helpingai · mradermacher
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
HE
HelpingAI 3B coder
Helpingai · QuantFactory
Params3.48B
Context125K
Q4_K_M2.1 GB
Coding
HE
HelpingAI-9B-200k
Helpingai · mradermacher
Params8.83B
Context195K
Q4_K_M5.3 GB
GGUF
HE
HelpingAI flash
Helpingai · mradermacher
Params2.24B
Context4K
Q4_K_M1.4 GB
GGUF
HE
HelpingAI 9B
Helpingai · QuantFactory
Params8.83B
Context4K
Q4_K_M5.3 GB
GGUF
HE
HelpingAI2.5 5B
Helpingai · mradermacher
Params5.13B
Context128K
Q4_K_M3.2 GB
GGUF
HE
HelpingAI Lite
Helpingai · mradermacher
Params1.1B
Context2K
Q4_K_M0.7 GB
Coding
HE
HelpingAI-9B
Helpingai · mradermacher
Params8.83B
Context4K
Q4_K_M5.3 GB
GGUF
HE
HelpingAI 3B hindi
Helpingai · QuantFactory
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
HE
HelpingAI 3B hindi
Helpingai · mradermacher
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
HE
HelpingAI Lite
Helpingai · QuantFactory
Params1.1B
Context2K
Q4_K_M0.7 GB
Coding
HE
HelpingAI-9B-200k
Helpingai · mradermacher
Params8.83B
Context195K
Q4_K_M5.3 GB
GGUF
HE
HelpingAI2 9B
Helpingai · bartowski
Params8.9B
Context128K
Q4_K_M5.4 GB
Tool use
HE
HelpingAI2.5 2B
Helpingai · mradermacher
Params1.71B
Context8K
Q4_K_M1.1 GB
GGUF
HE
HelpingAI2 6B
Helpingai · QuantFactory
Params5.85B
Context8K
Q4_K_M3.6 GB
GGUF
HE
HelpingAI2 9B
Helpingai · mradermacher
Params8.9B
Context128K
Q4_K_M5.4 GB
Tool use
HE
HelpingAI flash
Helpingai · QuantFactory
Params2.24B
Context4K
Q4_K_M1.4 GB
GGUF
HE
HelpingAI2.5 10B
Helpingai · mradermacher
Params10.2B
Context128K
Q4_K_M6.2 GB
Tool use
HE
HelpingAI-9B
Helpingai · bartowski
Params8.83B
Context4K
Q4_K_M5.3 GB
GGUF
HE
HelpingAI function
Helpingai · mradermacher
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
HE
HAI3 RAW
Helpingai · mradermacher
Params10.3B
Context32K
Q4_K_M6.3 GB
GGUF
HE
HelpingAI2.5 10B
Helpingai · mradermacher
Params10.2B
Context128K
Q4_K_M6.2 GB
Tool use
HE
Helpingai3 Raw
Helpingai · bartowski
Params10.3B
Context32K
Q4_K_M6.3 GB
GGUF
HE
HelpingAI2 3B
Helpingai · HelpingAI
Params2.81B
Context128K
Q4_K_M1.8 GB
Tool use
HE
HelpingAI2.5 5B
Helpingai · HelpingAI
Params5.13B
Context128K
Q4_K_M3.2 GB
Tool use
HE
HelpingAI2 9B
Helpingai · QuantFactory
Params8.9B
Context128K
Q4_K_M5.4 GB
Tool use
HE
HelpingAI Lite 2x1B
Helpingai · mradermacher
Params1.86B
Context2K
Q4_K_M1.1 GB
Coding
HE
HelpingAI Lite
Helpingai · OEvortex
Params1.1B
Context2K
Q4_K_M0.7 GB
Coding

About the Helpingai GGUF models

Helpingai is represented on ggufmodels.com by 79 GGUF models, quantized by 14 uploaders on Hugging Face. The most downloaded are HelpingAI-15B, HelpingAI-9B and HelpingAI 3B hindi i1. Parameter counts run from 110M to 17.5B, and the longest trained context window is 1024K tokens.

A Q4_K_M file of a Helpingai model is between 0.1 to 10.6 GB, which is the quant most people start with. Most files come from mradermacher (36), QuantFactory (10) and HelpingAI (8). The quants you will meet most often are Q4_K_M (71), Q2_K (58), Q3_K_M (57) and Q5_K_M (56), where the number is how many models offer that quant.

Frequently asked questions

Which Helpingai GGUF should I download?

The most downloaded Helpingai GGUF here is HelpingAI-15B. 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 Helpingai model need?

Q4_K_M files of Helpingai models on this site range from 0.1 to 10.6 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 Helpingai GGUF files come from?

The most common quantizers here are mradermacher, QuantFactory and HelpingAI. 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