RO

Models DavidAU L3.2 Rogue Creative Instruct Uncensored Abliterated 7B

RogueGGUF by MaziyarPanahiUpdated 2024-11-01
Download on Hugging Face
Parameters7.53B
Context128K
Layers67
Architecturellama
Smallest quant5.2 GB
Quick answer

Models DavidAU L3.2 Rogue Creative Instruct Uncensored Abliterated 7B needs about 8.9 GB of memory at Q6_K (a 6.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 5.2 GB (Q5_K_S) to 15.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 9.0 GB.

Models DavidAU L3.2 Rogue Creative Instruct Uncensored Abliterated 7B is a 7.53B-parameter Rogue model in GGUF format, quantized by MaziyarPanahi. Its trained context length is 128K tokens. The repository has 5 quant files, from 5.2 GB (Q5_K_S) to 15.1 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_S5.2 GB 8.0 GB
Tight Get file →
Q5_K_M5.4 GB 8.1 GB
Too big Get file →
Q6_K6.2 GB 8.9 GB
Too big Get file →
Q8_08.0 GB 10.8 GB
Too big Get file →
—15.1 GB 17.8 GB
Too big Get file →

What GPU do you need for Models DavidAU L3.2 Rogue Creative Instruct Uncensored Abliterated 7B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q5_K_S (5.2 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 10.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 10.8 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (15.1 GB file, about 17.8 GB in use).

Which Models DavidAU L3.2 Rogue Creative Instruct Uncensored Abliterated 7B quant should you choose?

Q6_K (6.2 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q5_K_S at 5.2 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.53B
Layers67
Trained context131,072 tokens
KV cache (fp16)268 KB per token

Frequently asked questions about Models DavidAU L3.2 Rogue Creative Instruct Uncensored Abliterated 7B

How much VRAM does Models DavidAU L3.2 Rogue Creative Instruct Uncensored Abliterated 7B need?

About 8.9 GB at Q6_K with an 8K context window. That is the 6.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Models DavidAU L3.2 Rogue Creative Instruct Uncensored Abliterated 7B on an 8 GB GPU?

Yes, with Q5_K_S: the 5.2 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Models DavidAU L3.2 Rogue Creative Instruct Uncensored Abliterated 7B GGUF?

It depends on the quant: Q5_K_S is 5.2 GB, Q5_K_M is 5.4 GB, Q6_K is 6.2 GB, Q8_0 is 8.0 GB, file is 15.1 GB.

What context length does Models DavidAU L3.2 Rogue Creative Instruct Uncensored Abliterated 7B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.2 GB at 8K and 9.0 GB at 32K.

Where can I download Models DavidAU L3.2 Rogue Creative Instruct Uncensored Abliterated 7B GGUF?

The files are on Hugging Face in the MaziyarPanahi/L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of L3.2-Rogue-Creative-Instruct-Uncensored-Abliterated-7B

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Rogue models

All Rogue →

Other small models

All small models →