Atlas GGUF models

70 GGUF models in the Atlas family, quantized by 26 uploaders. Sizes run from 135M to 72.7B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
AT
N ATLaS
Atlas · QuantFactory
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
AT
ATLAS 8B Thinking
Atlas · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
Reasoning
AT
Atlas Chat 9B
Atlas · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
AT
ATLAS Teach 8B Instruct
Atlas · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
AT
OS Atlas Pro 7B
Atlas · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
AT
Atlas Chat 2B
Atlas · mradermacher
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
AT
OS Atlas Base 7B
Atlas · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Vision
AT
Atlas V0.6 Mini 8B
Atlas · mradermacher
Params8.19B
Context32K
Q4_K_M5.0 GB
Reasoning
AT
Atlas Coder 0.5B
Atlas · mradermacher
Params494M
Context32K
Q4_K_M0.4 GB
Coding
AT
ATLAS 8B Instruct
Atlas · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
AT
Atlas Chat 27B
Atlas · mradermacher
Params27.2B
Context8K
Q4_K_M16.6 GB
GGUF
AT
Atlas V0.5 0.5B
Atlas · mradermacher
Params521M
Context16K
Q4_K_M0.3 GB
ReasoningTool use
AT
Atlas Flash 1.5B Preview
Atlas · tinyopsec
Params1.78B
Context128K
Q4_K_M1.1 GB
Tool use
AT
Atlas 72B SVT Merged
Atlas · mradermacher
Params72.7B
Context32K
Q4_K_M47.4 GB
Tool use
AT
Atlas Coder 2 0.5B
Atlas · mradermacher
Params494M
Context32K
Q4_K_M0.4 GB
CodingTool use
AT
Atlas Chat 2B
Atlas · RichardErkhov
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
AT
ATLAS Teach 8B Instruct
Atlas · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
AT
OS Atlas Base 7B
Atlas · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
AT
ATLAS 8B Thinking
Atlas · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
AT
Atlas Coder 2 0.5B
Atlas · Pluto-AI-Labs
Params494M
Context32K
Q4_K_M0.4 GB
CodingTool use
AT
Atlas Chat 9B
Atlas · RichardErkhov
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
AT
Atlas Coder 0.5B
Atlas · mradermacher
Params494M
Context32K
Q4_K_M0.4 GB
Coding
AT
WazoCore 8B v6 long
Atlas · mkbadeniyi
Params8.15B
Context128K
Q4_K_M5.0 GB
Tool use
AT
ATLAS 8B Instruct
Atlas · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
AT
Al Atlas LLM Large
Atlas · mradermacher
Params1.71B
Context8K
Q4_K_M1.1 GB
GGUF
AT
Atlas 7B i1
Atlas · mradermacher
Params7.77B
Context8K
Q4_K_M4.9 GB
GGUF
AT
Atlas Coder 2 0.5B
Atlas · mradermacher
Params494M
Context32K
Q4_K_M0.4 GB
CodingTool use
AT
Atlas Axiom 1.5b
Atlas · mradermacher
Params1.54B
Context32K
Q4_K_M1.0 GB
ReasoningTool use
AT
Atlas 72B SVT Merged
Atlas · mradermacher
Params72.7B
Context32K
Q4_K_M47.4 GB
Tool use
AT
Atlas Chat 27B
Atlas · RichardErkhov
Params27.2B
Context8K
Q4_K_M16.6 GB
GGUF

About the Atlas GGUF models

Atlas is represented on ggufmodels.com by 70 GGUF models, quantized by 26 uploaders on Hugging Face. The most downloaded are N ATLaS, ATLAS 8B Thinking and Atlas Chat 9B. Parameter counts run from 135M to 72.7B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Atlas model is between 0.1 to 47.4 GB, which is the quant most people start with. Most files come from mradermacher (37), ikramknd (4) and RichardErkhov (3). The quants you will meet most often are Q4_K_M (56), Q2_K (46), Q6_K (45) and Q5_K_M (45), where the number is how many models offer that quant.

Frequently asked questions

Which Atlas GGUF should I download?

The most downloaded Atlas GGUF here is N ATLaS. 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 Atlas model need?

Q4_K_M files of Atlas models on this site range from 0.1 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 Atlas GGUF files come from?

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