Apertus GGUF models

131 GGUF models in the Apertus family, quantized by 32 uploaders. Sizes run from 438M to 70.6B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
AP
Apertus-8B-Instruct-2509
Apertus · unsloth
Params8.05B
Context64K
Q4_K_M5.1 GB
GGUF
AP
Apertus-70B-Instruct-2509
Apertus · unsloth
Params70.6B
Context64K
Q4_K_M43.7 GB
GGUF
AP
Apertus 70B Instruct 2509 Abliterated
Apertus · mradermacher
Params70.6B
Context64K
Q4_K_M43.7 GB
GGUF
AP
Apertus 8B Instruct 2509
Apertus · bartowski
Params8.05B
Context64K
Q4_K_M5.1 GB
GGUF
AP
Apertus SEA LION v4 8B IT
Apertus · aisingapore
Params8.05B
Context64K
Q4_K_M5.1 GB
ReasoningTool use
AP
Apertus 70B Instruct 2509
Apertus · bartowski
Params70.6B
Context64K
Q4_K_M43.7 GB
GGUF
AP
Apertus 8B Instruct 2509 Heretic
Apertus · mradermacher
Params8.05B
Context64K
Q4_K_M5.1 GB
ReasoningTool use
AP
Apertus 8B MeditronFO
Apertus · mradermacher
Params8.05B
Context64K
Q4_K_M5.1 GB
ReasoningTool use
AP
Apertus 8B Instruct 2509
Apertus · mradermacher
Params8.05B
Context64K
Q4_K_M5.1 GB
GGUF
AP
Apertus 8B Instruct heretic
Apertus · saidutta69
Params8.05B
Context64K
Q4_K_M5.1 GB
ReasoningRoleplayTool use
AP
Apertus v1.5 8b Text
Apertus · Colby
Params8.05B
Context256K
Q4_K_M5.1 GB
ReasoningTool use
AP
Apertus 8b Instruct Patched
Apertus · mradermacher
Params8.05B
Context64K
Q4_K_M5.1 GB
GGUF
AP
Walnoot 8B Instruct
Apertus · WAINUT
Params8.05B
Context64K
Smallest16.1 GB
GGUF
AP
Apertus 8B MeditronFO
Apertus · mradermacher
Params8.05B
Context64K
Q4_K_M5.1 GB
ReasoningTool use
AP
Apertus 8b Swiss Insurance
Apertus · mradermacher
Params8.05B
Context64K
Q4_K_M5.1 GB
ReasoningTool use
AP
Apertus EstLLM 8B 1125
Apertus · mradermacher
Params8.05B
Context64K
Q4_K_M5.1 GB
GGUF
AP
Apertus 8B Instruct 2509 Abliterated
Apertus · mradermacher
Params8.05B
Context64K
Q4_K_M5.1 GB
ReasoningTool use
AP
Apertus v1.1 4B Instruct
Apertus · jondale
Params3.83B
Context4K
Q4_K_M2.4 GB
Tool use
AP
Apertus v1.5 8b Text
Apertus · andreasmartin
Params8.05B
Context256K
Smallest8.6 GB
ReasoningTool use
AP
Apertus 70B Instruct 2509 Heretic v3
Apertus · mradermacher
Params70.6B
Context64K
Q4_K_M43.7 GB
ReasoningTool use
AP
Apertus 8B Instruct 2509
Apertus · giladgd
Params8.05B
Context64K
Q4_K_M5.1 GB
GGUF
AP
Apertus 70B MeditronFO
Apertus · mradermacher
Params70.6B
Context64K
Q4_K_M43.7 GB
ReasoningTool use
AP
Apertus 70B Instruct 2509 Heretic v2
Apertus · mradermacher
Params70.6B
Context64K
Q4_K_M43.7 GB
ReasoningTool use
AP
Apertus 8B Tulu3 Eng
Apertus · mradermacher
Params8.05B
Context64K
Q4_K_M5.1 GB
GGUF
AP
Apertus 8B Instruct Heretic
Apertus · mradermacher
Params8.05B
Context64K
Q4_K_M5.1 GB
ReasoningTool use
AP
Apertus SEA LION v4 8B IT
Apertus · mradermacher
Params8.05B
Context64K
Q4_K_M5.1 GB
ReasoningTool use
AP
Apertus EstLLM 8B Instruct 1125
Apertus · mradermacher
Params8.05B
Context64K
Q4_K_M5.1 GB
ReasoningTool use
AP
Apertus v1.1 1.5B
Apertus · mradermacher
Params1.51B
Context4K
Q4_K_M1.0 GB
GGUF
AP
Apertus EstLLM 8B Instruct 1125
Apertus · mradermacher
Params8.05B
Context64K
Q4_K_M5.1 GB
ReasoningTool use
AP
Apertus 8B Instruct 2509 Abliterated
Apertus · mradermacher
Params8.05B
Context64K
Q4_K_M5.1 GB
ReasoningTool use

About the Apertus GGUF models

Apertus is represented on ggufmodels.com by 131 GGUF models, quantized by 32 uploaders on Hugging Face. The most downloaded are Apertus-8B-Instruct-2509, Apertus-70B-Instruct-2509 and Apertus 70B Instruct 2509 Abliterated. Parameter counts run from 438M to 70.6B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Apertus model is between 0.3 to 43.7 GB, which is the quant most people start with. Most files come from mradermacher (59), NonMiFrega (14) and Colby (6). The quants you will meet most often are Q4_K_M (103), Q5_K_M (85), Q6_K (72) and Q3_K_M (69), where the number is how many models offer that quant.

Frequently asked questions

Which Apertus GGUF should I download?

The most downloaded Apertus GGUF here is Apertus-8B-Instruct-2509. 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 Apertus model need?

Q4_K_M files of Apertus models on this site range from 0.3 to 43.7 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 Apertus GGUF files come from?

The most common quantizers here are mradermacher, NonMiFrega and Colby. 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