Forgotten GGUF models

106 GGUF models in the Forgotten family, quantized by 13 uploaders. Sizes run from 8.02B to 70.6B parameters. The longest trained context is 1000K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
FO
ReadyArt Forgotten Safeword 12B 3.6
Forgotten · bartowski
Params12.2B
Context128K
Q4_K_M7.5 GB
RoleplayTool use
FO
ReadyArt Forgotten Safeword 70B 3.6
Forgotten · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
Roleplay
FO
ReadyArt Forgotten Safeword 24B 3.6
Forgotten · bartowski
Params23.6B
Context32K
Q4_K_M14.3 GB
Roleplay
FO
Forgotten Safeword 12B v4.0 i1
Forgotten · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
RoleplayTool use
FO
Forgotten Abomination 24B v4.0 i1
Forgotten · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
Roleplay
FO
Forgotten Safeword 24B i1
Forgotten · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
Roleplay
FO
Forgotten Hubris 24B v0.1
Forgotten · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Tool use
FO
Forgotten Safeword 24B 3.6 i1
Forgotten · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
Roleplay
FO
Forgotten Safeword 70B v5.0 i1
Forgotten · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Roleplay
FO
Forgotten_Magic_24B
Forgotten · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
RoleplayTool use
FO
Forgotten Abomination 70B v5.0
Forgotten · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Roleplay
FO
Forgotten Abomination 12B v4.0
Forgotten · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
RoleplayTool use
FO
Forgotten Safeword 12B v4.0
Forgotten · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
RoleplayTool use
FO
Forgotten Abomination 36B v4.1 Uncensored Heretic
Forgotten · mradermacher
Params36.9B
Context32K
Q4_K_M22.4 GB
Roleplay
FO
Forgotten Abomination 12B v4.0 i1
Forgotten · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
RoleplayTool use
FO
Forgotten Transgression 24B v4.1
Forgotten · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
Roleplay
FO
Forgotten Abomination 36B v4.1 Ultra Uncensored Heretic
Forgotten · mradermacher
Params36.9B
Context32K
Q4_K_M22.4 GB
Roleplay
FO
Forgotten Safeword 70B v5.0 Heretic
Forgotten · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Roleplay
FO
Forgotten Safeword 8B V2.2 i1
Forgotten · mradermacher
Params8.02B
Context32K
Q4_K_M4.9 GB
Tool use
FO
Forgotten Safeword 24B v4.0 i1
Forgotten · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
Roleplay
FO
Forgotten Safeword 8B V3.0 i1
Forgotten · mradermacher
Params8.02B
Context32K
Q4_K_M4.9 GB
RoleplayTool use
FO
Forgotten Abomination 8B v4.0 i1
Forgotten · mradermacher
Params8.02B
Context32K
Q4_K_M4.9 GB
RoleplayTool use
FO
Forgotten Abomination 70B v5.0 i1
Forgotten · mradermacher
Params70.6B
Context128K
Q4_K_M42.5 GB
Roleplay
FO
Forgotten Safeword 24B V2.2 i1
Forgotten · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
Roleplay
FO
Forgotten Safeword 22B i1
Forgotten · mradermacher
Params22.2B
Context32K
Q4_K_M13.3 GB
RoleplayTool use
FO
Forgotten Abomination 24B V2.2
Forgotten · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
FO
Forgotten Transgression 24B v4.1 Uncensored Heretic
Forgotten · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
Roleplay
FO
Forgotten Safeword 8B v4.0 i1
Forgotten · mradermacher
Params8.02B
Context32K
Q4_K_M4.9 GB
RoleplayTool use
FO
Forgotten Abomination 24B 3.4 i1
Forgotten · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
FO
Forgotten Safeword 12B 3.6
Forgotten · mradermacher
Params12.2B
Context128K
Q4_K_M7.5 GB
RoleplayTool use

About the Forgotten GGUF models

Forgotten is represented on ggufmodels.com by 106 GGUF models, quantized by 13 uploaders on Hugging Face. The most downloaded are ReadyArt Forgotten Safeword 12B 3.6, ReadyArt Forgotten Safeword 70B 3.6 and ReadyArt Forgotten Safeword 24B 3.6. Parameter counts run from 8.02B to 70.6B, and the longest trained context window is 1000K tokens.

A Q4_K_M file of a Forgotten model is between 4.9 to 42.5 GB, which is the quant most people start with. Most files come from mradermacher (82), Ransss (6) and llmfan46 (4). The quants you will meet most often are Q4_K_M (92), Q5_K_M (90), Q5_K_S (89) and Q6_K (88), where the number is how many models offer that quant.

Frequently asked questions

Which Forgotten GGUF should I download?

The most downloaded Forgotten GGUF here is ReadyArt Forgotten Safeword 12B 3.6. 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 Forgotten model need?

Q4_K_M files of Forgotten models on this site range from 4.9 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 Forgotten GGUF files come from?

The most common quantizers here are mradermacher, Ransss and llmfan46. 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