NO

Norquinal_Jamba-v0.1-Claude-Chat

NorquinalGGUF by SeverianUpdated 2024-05-31
Download on Hugging Face
Parameters51.6B
Context256K
Layers32
Architecturejamba
Smallest quant42.7 GB
Quick answer

Norquinal_Jamba-v0.1-Claude-Chat needs about 47.5 GB of memory at Q6_K (a 42.7 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 17.2 GB.

Norquinal_Jamba-v0.1-Claude-Chat is a 51.6B-parameter Norquinal model in GGUF format, quantized by Severian. Its trained context length is 256K tokens. The repository has 1 quant file, from 42.7 GB (Q6_K) to 42.7 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K42.7 GB 47.5 GB
Too big Get file →

What GPU do you need for Norquinal_Jamba-v0.1-Claude-Chat?

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 Q6_K (42.7 GB file, about 47.5 GB in use).

Which Norquinal_Jamba-v0.1-Claude-Chat quant should you choose?

Q6_K (42.7 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturejamba
Parameters51.6B (approximate, mixture of experts)
Layers32
Trained context262,144 tokens
KV cache (fp16)512 KB per token

Source

Quantized bySeverian
FamilyNorquinal
Licenseapache-2.0
Downloads (HF)51
Last updated2024-05-31

Frequently asked questions about Norquinal_Jamba-v0.1-Claude-Chat

How much VRAM does Norquinal_Jamba-v0.1-Claude-Chat need?

About 47.5 GB at Q6_K with an 8K context window. That is the 42.7 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 Norquinal_Jamba-v0.1-Claude-Chat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 47.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Norquinal_Jamba-v0.1-Claude-Chat GGUF?

It depends on the quant: Q6_K is 42.7 GB.

What context length does Norquinal_Jamba-v0.1-Claude-Chat support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.

Where can I download Norquinal_Jamba-v0.1-Claude-Chat GGUF?

The files are on Hugging Face in the Severian/Jamba-v0.1-Claude-Chat-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 Norquinal_Jamba-v0.1-Claude-Chat use?

Hugging Face lists the license as apache-2.0. 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 from Severian

All by Severian →

Other large models

All large models →