Jais GGUF models

103 GGUF models in the Jais family, quantized by 12 uploaders. Sizes run from 385M to 72.7B parameters. The longest trained context is 512K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
JA
Jais-3-32B
Jais · mradermacher
Params34.8B
Context512K
Q4_K_M21.1 GB
ReasoningTool use
JA
Jais-3-32B
Jais · mradermacher
Params34.8B
Context512K
Q4_K_M21.1 GB
Reasoning
JA
Jais-3-MoVA-36B-A4B
Jais · mradermacher
Params37.4B
Context512K
Q4_K_M22.4 GB
Reasoning
JA
Jais-3-7B
Jais · mradermacher
Params9B
Context512K
Q4_K_M5.6 GB
Reasoning
JA
Jais adapted 7B Reflection Tuning Natural Farmer i1
Jais · mradermacher
Params7B
Context4K
Q4_K_M4.3 GB
GGUF
JA
Jais-3-3.7B
Jais · mradermacher
Params5.06B
Context512K
Q4_K_M3.2 GB
Reasoning
JA
Jais-3-3.7B
Jais · IFM
Params5.06B
Context512K
Q4_K_M3.2 GB
ReasoningTool use
JA
Jais Adapted 70b Chat
Jais · RichardErkhov
Params69.5B
Context4K
Q4_K_M41.8 GB
GGUF
JA
Jais-3-7B
Jais · IFM
Params9B
Context512K
Q4_K_M5.6 GB
ReasoningTool use
JA
Jais-3-MoVA-36B-A4B
Jais · IFM
Params37.4B
Context512K
Q4_K_M22.4 GB
ReasoningTool use
JA
Jais-3-32B
Jais · IFM
Params34.8B
Context512K
Q4_K_M21.1 GB
ReasoningTool use
JA
Jais Adapted 7b Chat
Jais · mradermacher
Params7B
Context4K
Q4_K_M4.3 GB
Coding
JA
Jais adapted 7B Reflection Tuning Natural Farmer
Jais · mradermacher
Params7B
Context4K
Q4_K_M4.3 GB
GGUF
JA
Jais ASR
Jais · IFM
Params5.06B
Context512K
Q4_K_M3.2 GB
CodingVision
JA
Jais Adapted 70b Chat
Jais · mradermacher
Params69.5B
Context4K
Q4_K_M41.8 GB
Coding
JA
Jais Family 13b Chat
Jais · mradermacher
Params13.5B
Context2K
Q4_K_M9.0 GB
Coding
JA
Jais Adapted 70b
Jais · mradermacher
Params69.5B
Context4K
Q4_K_M41.8 GB
Coding
JA
Jais Adapted 7b Chat
Jais · QuantFactory
Params7B
Context4K
Q4_K_M4.3 GB
Coding
JA
Jais Family 6p7b Chat
Jais · mradermacher
Params7.14B
Context2K
Q4_K_M6.4 GB
Coding
JA
Jais-Inception-70b-V1.2.2
Jais · mradermacher
Params72.7B
Context128K
Q4_K_M47.4 GB
GGUF
JA
Jais-3-7B
Jais · mradermacher
Params9B
Context512K
Q4_K_M5.6 GB
ReasoningTool use
JA
Jais Family 6p7b
Jais · mradermacher
Params7.14B
Context2K
Q4_K_M6.4 GB
Coding
JA
Jais Family 30b 16k Chat
Jais · mradermacher
Params30.8B
Context16K
Q4_K_M27.9 GB
Coding
JA
Jais-3-3.7B
Jais · mradermacher
Params5.06B
Context512K
Q4_K_M3.2 GB
ReasoningTool use
JA
Jais-3-7B
Jais · webmp3
Params9B
Context512K
Q4_K_M5.6 GB
ReasoningTool use
JA
Jais-3-MoVA-36B-A4B
Jais · mradermacher
Params37.4B
Context512K
Q4_K_M22.4 GB
ReasoningTool use
JA
Jais Family 13b
Jais · mradermacher
Params13.5B
Context2K
Q4_K_M9.0 GB
Coding
JA
Jais Family 2p7b
Jais · mradermacher
Params2.95B
Context2K
Q4_K_M2.6 GB
Coding
JA
Jais-3-0.9B
Jais · IFM
Params1.08B
Context128K
Q4_K_M0.7 GB
ReasoningTool use
JA
Jais-3-0.9B
Jais · mradermacher
Params1.08B
Context128K
Q4_K_M0.7 GB
ReasoningTool use

About the Jais GGUF models

Jais is represented on ggufmodels.com by 103 GGUF models, quantized by 12 uploaders on Hugging Face. The most downloaded are Jais-3-32B, Jais-3-32B and Jais-3-MoVA-36B-A4B. Parameter counts run from 385M to 72.7B, and the longest trained context window is 512K tokens.

A Q4_K_M file of a Jais model is between 0.3 to 47.4 GB, which is the quant most people start with. Most files come from mradermacher (63), RichardErkhov (8) and NikolayKozloff (6). The quants you will meet most often are Q4_K_M (90), Q5_K_M (80), Q2_K (77) and Q3_K_M (76), where the number is how many models offer that quant.

Frequently asked questions

Which Jais GGUF should I download?

The most downloaded Jais GGUF here is Jais-3-32B. 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 Jais model need?

Q4_K_M files of Jais models on this site range from 0.3 to 47.4 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 Jais GGUF files come from?

The most common quantizers here are mradermacher, RichardErkhov and NikolayKozloff. 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