JA

Jamba-v0.1-hf

JambaGGUF by TechxGenusUpdated 2024-05-26
Download on Hugging Face
Parameters51.6B
Context256K
Layers32
Architecturejamba
Smallest quant103.4 GB
Quick answer

Jamba-v0.1-hf needs about 108.2 GB of memory at its main file (a 103.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

Jamba-v0.1-hf is a 51.6B-parameter Jamba model in GGUF format, quantized by TechxGenus. Its trained context length is 256K tokens. The repository has 1 quant file, from 103.4 GB to 103.4 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—103.4 GB (24 parts) 108.2 GB
Too big Get file →

What GPU do you need for Jamba-v0.1-hf?

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: no quant fits at an 8K context.

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 byTechxGenus
FamilyJamba
Downloads (HF)25
Last updated2024-05-26

Frequently asked questions about Jamba-v0.1-hf

How much VRAM does Jamba-v0.1-hf need?

About 108.2 GB at its main file with an 8K context window. That is the 103.4 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 Jamba-v0.1-hf on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 108.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Jamba-v0.1-hf GGUF?

It depends on the quant: file is 103.4 GB.

What context length does Jamba-v0.1-hf 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 Jamba-v0.1-hf GGUF?

The files are on Hugging Face in the TechxGenus/Jamba-v0.1-hf-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More Jamba models

All Jamba →

Other large models

All large models →