FL

FLOR 6.3B

FlorGGUF by xaviviroUpdated 2024-01-08
Download on Hugging Face
Parameters6.45B
Context4K
Layers30
Architecturebloom
Smallest quant2.7 GB
Quick answer

FLOR 6.3B needs about 9.0 GB of memory at Q5_0 (a 4.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 2.7 GB (Q2_K) to 12.9 GB (F16).

FLOR 6.3B is a 6.45B-parameter Flor model in GGUF format, quantized by xaviviro. Its trained context length is 4K tokens. The repository has 11 quant files, from 2.7 GB (Q2_K) to 12.9 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.7 GB 5.2 GB
Fits Get file →
Q3_K_S2.9 GB 5.4 GB
Fits Get file →
Q4_03.7 GB 6.2 GB
Fits Get file →
Q3_K_L3.7 GB 6.2 GB
Fits Get file →
Q4_K_S3.7 GB 6.2 GB
Fits Get file →
Q5_04.5 GB 7.0 GB
Fits Get file →
Q5_K_S4.5 GB 7.0 GB
Fits Get file →
Q5_K_M4.8 GB 7.3 GB
Tight Get file →
Q5_14.9 GB 7.4 GB
Tight Get file →
Q8_06.9 GB 9.4 GB
Too big Get file →
F1612.9 GB 15.4 GB
Too big Get file →

What GPU do you need for FLOR 6.3B?

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: the best quant that fits is Q3_K_S (2.9 GB file, about 7.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (6.9 GB file, about 11.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (6.9 GB file, about 11.4 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (12.9 GB file, about 17.4 GB in use).

Which FLOR 6.3B quant should you choose?

Q5_0 (4.5 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q2_K at 2.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturebloom
Parameters6.45B
Layers30
Trained context4,096 tokens
KV cache (fp16)480 KB per token

Source

Quantized byxaviviro
FamilyFlor
Downloads (HF)524
Last updated2024-01-08

Frequently asked questions about FLOR 6.3B

How much VRAM does FLOR 6.3B need?

About 9.0 GB at Q5_0 with an 8K context window. That is the 4.5 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 FLOR 6.3B on an 8 GB GPU?

Yes, with Q3_K_S: the 2.9 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of FLOR 6.3B GGUF?

It depends on the quant: Q2_K is 2.7 GB, Q3_K_S is 2.9 GB, Q4_0 is 3.7 GB, Q3_K_L is 3.7 GB, Q4_K_S is 3.7 GB, Q5_0 is 4.5 GB and 5 more.

What context length does FLOR 6.3B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.0 GB at 8K and 2.0 GB at 4K.

Where can I download FLOR 6.3B GGUF?

The files are on Hugging Face in the xaviviro/FLOR-6.3B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of FLOR-6.3B

Similar models

Browse all →

More from xaviviro

All by xaviviro →

More Flor models

All Flor →

Other small models

All small models →