VI

visa chat 400 7b e2 f32

VisaGGUF by skaty5678Updated 2024-06-01
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant27.0 GB
Quick answer

visa chat 400 7b e2 f32 needs about 31.7 GB of memory at F32 (a 27.0 GB file) with an 8K context window, so it fits on a 32 GB GPU.

visa chat 400 7b e2 f32 is a 6.74B-parameter Visa model in GGUF format, quantized by skaty5678. Its trained context length is 4K tokens. The repository has 1 quant file, from 27.0 GB (F32) to 27.0 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F3227.0 GB 29.6 GB
Too big Get file →

What GPU do you need for visa chat 400 7b e2 f32?

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: the best quant that fits is F32 (27.0 GB file, about 31.7 GB in use).

Which visa chat 400 7b e2 f32 quant should you choose?

F32 (27.0 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byskaty5678
FamilyVisa
Downloads (HF)9
Last updated2024-06-01

Frequently asked questions about visa chat 400 7b e2 f32

How much VRAM does visa chat 400 7b e2 f32 need?

About 31.7 GB at F32 with an 8K context window. That is the 27.0 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 visa chat 400 7b e2 f32 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 31.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of visa chat 400 7b e2 f32 GGUF?

It depends on the quant: F32 is 27.0 GB.

What context length does visa chat 400 7b e2 f32 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download visa chat 400 7b e2 f32 GGUF?

The files are on Hugging Face in the skaty5678/visa-chat-400-7b-e2-f32-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 from skaty5678

All by skaty5678 →

More Visa models

All Visa →

Other small models

All small models →