FL

FlatDolphinMaid 8x7B

FlatdolphinmaidGGUF by tsunemotoUpdated 2024-01-04
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant15.5 GB
Quick answer

FlatDolphinMaid 8x7B needs about 27.9 GB of memory at Q4_K_M (a 26.3 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 14 quants, from 15.5 GB (Q2_K) to 49.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

FlatDolphinMaid 8x7B is a 46.7B-parameter Flatdolphinmaid model in GGUF format, quantized by tsunemoto. Its trained context length is 32K tokens. The repository has 14 quant files, from 15.5 GB (Q2_K) to 49.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K15.5 GB 17.0 GB
Too big Get file →
Q3_K_S20.1 GB 21.7 GB
Too big Get file →
Q3_K_M20.2 GB 21.8 GB
Too big Get file →
Q3_K_L20.3 GB 21.9 GB
Too big Get file →
Q4_026.3 GB 27.9 GB
Too big Get file →
Q4_K_S26.3 GB 27.9 GB
Too big Get file →
Q4_K_M26.3 GB 27.9 GB
Too big Get file →
Q4_129.2 GB 30.8 GB
Too big Get file →
Q5_032.1 GB 33.7 GB
Too big Get file →
Q5_K_S32.1 GB 33.7 GB
Too big Get file →
Q5_K_M32.1 GB 33.7 GB
Too big Get file →
Q5_135.0 GB 36.6 GB
Too big Get file →
Q6_K38.3 GB 39.9 GB
Too big Get file →
Q8_049.6 GB 51.2 GB
Too big Get file →

What GPU do you need for FlatDolphinMaid 8x7B?

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: the best quant that fits is Q3_K_L (20.3 GB file, about 21.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_1 (29.2 GB file, about 30.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (38.3 GB file, about 39.9 GB in use).

Which FlatDolphinMaid 8x7B quant should you choose?

Q4_K_M is the usual starting point for FlatDolphinMaid 8x7B: it balances file size and quality well. Here it is a 26.3 GB file.

The Q8_0 file is 49.6 GB, about 1.9 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 15.5 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

Architecturellama
Parameters46.7B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bytsunemoto
Downloads (HF)335
Last updated2024-01-04

Frequently asked questions about FlatDolphinMaid 8x7B

How much VRAM does FlatDolphinMaid 8x7B need?

About 27.9 GB at Q4_K_M with an 8K context window. That is the 26.3 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 FlatDolphinMaid 8x7B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of FlatDolphinMaid 8x7B GGUF?

It depends on the quant: Q2_K is 15.5 GB, Q3_K_S is 20.1 GB, Q3_K_M is 20.2 GB, Q3_K_L is 20.3 GB, Q4_0 is 26.3 GB, Q4_K_S is 26.3 GB and 8 more.

What context length does FlatDolphinMaid 8x7B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download FlatDolphinMaid 8x7B GGUF?

The files are on Hugging Face in the tsunemoto/FlatDolphinMaid-8x7B-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 tsunemoto

All by tsunemoto →

More Flatdolphinmaid models

All Flatdolphinmaid →

Other large models

All large models →