ME

meditron ft 7b v1 Q8 0

MeditronGGUF by davidneneUpdated 2024-09-22
Download on Hugging Face
Parameters7B
Context2K
Layers32
Architecturellama
Smallest quant0.0 GB
Quick answer

meditron ft 7b v1 Q8 0 needs about 4.8 GB of memory at Q8_0 (a 0.0 GB file) with an 8K context window, so it fits on a 6 GB GPU.

meditron ft 7b v1 Q8 0 is a 7B-parameter Meditron model in GGUF format, quantized by davidnene. Its trained context length is 2K tokens. The repository has 1 quant file, from 0.0 GB (Q8_0) to 0.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.0 GB 1.6 GB
Fits Get file →

What GPU do you need for meditron ft 7b v1 Q8 0?

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: the best quant that fits is Q8_0 (0.0 GB file, about 4.8 GB in use).

Which meditron ft 7b v1 Q8 0 quant should you choose?

Q8_0 (0.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7B
Layers32
Trained context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized bydavidnene
FamilyMeditron
Downloads (HF)3
Last updated2024-09-22

Frequently asked questions about meditron ft 7b v1 Q8 0

How much VRAM does meditron ft 7b v1 Q8 0 need?

About 4.8 GB at Q8_0 with an 8K context window. That is the 0.0 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 meditron ft 7b v1 Q8 0 on an 8 GB GPU?

Yes, with Q8_0: the 0.0 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of meditron ft 7b v1 Q8 0 GGUF?

It depends on the quant: Q8_0 is 0.0 GB.

What context length does meditron ft 7b v1 Q8 0 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.

Where can I download meditron ft 7b v1 Q8 0 GGUF?

The files are on Hugging Face in the davidnene/meditron-ft-7b-v1_Q8_0-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 Meditron models

All Meditron →

Other small models

All small models →