Apollo GGUF models

105 GGUF models in the Apollo family, quantized by 26 uploaders. Sizes run from 14M to 70.6B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
AP
Apollo Astralis 4b
Apollo · mradermacher
Params4B
Context256K
Q4_K_M2.5 GB
Reasoning
AP
Apollo 1 8B
Apollo · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
AP
Apollo V0.1 4B Thinking
Apollo · bartowski
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
AP
Nous V1 8B
Apollo · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
AP
Apollo VL Edge 3B
Apollo · mradermacher
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision
AP
Apollo VL Edge 3B FP16
Apollo · Pluto-AI-Labs
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision
AP
Apollo 1 4B
Apollo · mradermacher
Params4.02B
Context128K
Q4_K_M2.5 GB
ReasoningTool use
AP
Apollo-7B
Apollo · mradermacher
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
AP
Apollo V0.1 4B Thinking
Apollo · mradermacher
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
AP
Apollo 1 8B
Apollo · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
AP
Nous 1 8B
Apollo · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
AP
Apollo2 7B
Apollo · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
AP
Nous 1 4B
Apollo · mradermacher
Params4.02B
Context128K
Q4_K_M2.5 GB
ReasoningTool use
AP
Apollo v1 7b
Apollo · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
CodingReasoning
AP
Apollo VL Edge 3B
Apollo · mradermacher
Params3.09B
Context125K
Q4_K_M1.9 GB
Vision
AP
Apollo Astralis 2
Apollo · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
ReasoningRoleplayTool use
AP
Apollo2 1.5B
Apollo · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
GGUF
AP
Apollo Astralis 2
Apollo · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
ReasoningRoleplayTool use
AP
Nous V1 2B
Apollo · mradermacher
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
AP
Apollo 1 2B
Apollo · mradermacher
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
AP
Nous 1 2B f32
Apollo · prithivMLmods
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
AP
Nous 1 2B
Apollo · mradermacher
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
AP
Apollo2 9B
Apollo · mradermacher
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
AP
Nous V1 4B
Apollo · prithivMLmods
Params4.02B
Context128K
Q4_K_M2.5 GB
ReasoningTool use
AP
rootxhacker Apollo v3 32B
Apollo · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
AP
Apollo 1 4B
Apollo · mradermacher
Params4.02B
Context128K
Q4_K_M2.5 GB
ReasoningTool use
AP
Nous 1 2B
Apollo · mradermacher
Params1.72B
Context40K
Q4_K_M1.1 GB
ReasoningTool use
AP
Nous V1 4B
Apollo · mradermacher
Params4.02B
Context128K
Q4_K_M2.5 GB
ReasoningTool use
AP
Apollo 1.8B
Apollo · RichardErkhov
Params1.84B
Context8K
Q4_K_M1.2 GB
GGUF
AP
Apollo2 3.8B
Apollo · mradermacher
Params3.82B
Context4K
Q4_K_M2.4 GB
GGUF

About the Apollo GGUF models

Apollo is represented on ggufmodels.com by 105 GGUF models, quantized by 26 uploaders on Hugging Face. The most downloaded are Apollo Astralis 4b, Apollo 1 8B and Apollo V0.1 4B Thinking. Parameter counts run from 14M to 70.6B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Apollo model is between 0.3 to 42.5 GB, which is the quant most people start with. Most files come from mradermacher (55), itlwas (5) and RichardErkhov (5). The quants you will meet most often are Q4_K_M (86), Q2_K (77), Q5_K_M (75) and Q5_K_S (72), where the number is how many models offer that quant.

Frequently asked questions

Which Apollo GGUF should I download?

The most downloaded Apollo GGUF here is Apollo Astralis 4b. 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 Apollo model need?

Q4_K_M files of Apollo models on this site range from 0.3 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 Apollo GGUF files come from?

The most common quantizers here are mradermacher, itlwas 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