NO

nontoxic bagel 34b v0.2

NontoxicGGUF by rs0x29aUpdated 2024-01-11
Download on Hugging Face
Parameters34.4B
Context195K
Layers60
Architecturellama
Smallest quant36.5 GB
Quick answer

nontoxic bagel 34b v0.2 needs about 39.1 GB of memory at its main file (a 36.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

nontoxic bagel 34b v0.2 is a 34.4B-parameter Nontoxic model in GGUF format, quantized by rs0x29a. Its trained context length is 195K tokens. The repository has 1 quant file, from 36.5 GB to 36.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—36.5 GB 39.1 GB
Too big Get file →

What GPU do you need for nontoxic bagel 34b v0.2?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is the main file (36.5 GB file, about 39.1 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters34.4B
Layers60
Trained context200,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized byrs0x29a
FamilyNontoxic
Licensemit
Downloads (HF)6
Last updated2024-01-11

Frequently asked questions about nontoxic bagel 34b v0.2

How much VRAM does nontoxic bagel 34b v0.2 need?

About 39.1 GB at its main file with an 8K context window. That is the 36.5 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 nontoxic bagel 34b v0.2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 39.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of nontoxic bagel 34b v0.2 GGUF?

It depends on the quant: file is 36.5 GB.

What context length does nontoxic bagel 34b v0.2 support?

The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download nontoxic bagel 34b v0.2 GGUF?

The files are on Hugging Face in the rs0x29a/nontoxic-bagel-34b-v0.2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does nontoxic bagel 34b v0.2 use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More Nontoxic models

All Nontoxic →

Other large models

All large models →