Athena GGUF models

122 GGUF models in the Athena family, quantized by 17 uploaders. Sizes run from 494M to 120B parameters. The longest trained context is 1024K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
AT
Athena v1
Athena · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
AT
Athena v4
Athena · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
AT
Athena v2
Athena · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
AT
Athena v4 i1
Athena · mradermacher
Params13B
Context4K
Q4_K_M8.1 GB
GGUF
AT
Athena-CodePhi-7B-4k-v0.1
Athena · mradermacher
Params3.82B
Context4K
Q4_K_M2.3 GB
Coding
AT
Athena-CodeZephyr-7B-v0.2
Athena · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
AT
Athena Codegemma 2 9b
Athena · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
AT
Athena-OrpoMistral-7B-Chat-v0.1
Athena · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Tool use
AT
Athena v3
Athena · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
AT
Athena zephyr 7B
Athena · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
Coding
AT
Athena 1.0 4B
Athena · Pluto-AI-Labs
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
AT
Atlas Pro 7B Preview 1M i1
Athena · mradermacher
Params7.62B
Context986K
Q4_K_M4.7 GB
Tool use
AT
Athena Codegemma 2 9b
Athena · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
AT
athena 120b i1
Athena · mradermacher
Params120B
Context4K
Smallest26.1 GB
GGUF
AT
Atlas Pro 7B Preview i1
Athena · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Tool use
AT
Athena Codegemma 2 9b
Athena · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
AT
Athena 1 14B i1
Athena · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use
AT
Athena Codegemma 2 9b v1
Athena · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
AT
Atlas Pro 7B Preview 1M
Athena · aayanmishra-ml
Params7.62B
Context986K
Q4_K_M4.7 GB
Tool use
AT
Athena R3X 8B
Athena · mradermacher
Params8.19B
Context128K
Q4_K_M5.0 GB
Tool use
AT
Athena Codegemma 2 9b
Athena · QuantFactory
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
AT
Atlas Pro 7B Preview 1M
Athena · mradermacher
Params7.62B
Context986K
Q4_K_M4.7 GB
Tool use
AT
Athena 1 7B
Athena · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
AT
Athena v2
Athena · IkariDev
Params13B
Context4K
Smallest7.4 GB
GGUF
AT
L3.1 Athena g 8B i1
Athena · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
AT
Athena-70B-L3
Athena · mradermacher
Params70.6B
Context8K
Q4_K_M42.5 GB
GGUF
AT
Athena 1 14B
Athena · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use
AT
Athena v3
Athena · IkariDev
Params13B
Context4K
Smallest7.4 GB
GGUF
AT
Athena 1 3B i1
Athena · mradermacher
Params3.09B
Context32K
Q4_K_M1.9 GB
Tool use
AT
Ares 4B
Athena · mradermacher
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use

About the Athena GGUF models

Athena is represented on ggufmodels.com by 122 GGUF models, quantized by 17 uploaders on Hugging Face. The most downloaded are Athena v1, Athena v4 and Athena v2. Parameter counts run from 494M to 120B, and the longest trained context window is 1024K tokens.

A Q4_K_M file of a Athena model is between 0.4 to 42.5 GB, which is the quant most people start with. Most files come from mradermacher (84), aayanmishra-ml (7) and itlwas (5). The quants you will meet most often are Q4_K_M (105), Q5_K_M (103), Q2_K (98) and Q4_K_S (97), where the number is how many models offer that quant.

Frequently asked questions

Which Athena GGUF should I download?

The most downloaded Athena GGUF here is Athena v1. 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 Athena model need?

Q4_K_M files of Athena models on this site range from 0.4 to 42.5 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 Athena GGUF files come from?

The most common quantizers here are mradermacher, aayanmishra-ml and itlwas. 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