DE

Dendrite L3 10B iMat

DendriteGGUF by Quant-CartelUpdated 2024-05-05
Download on Hugging Face
Parameters9.78B
Context8K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

Dendrite L3 10B iMat needs about 7.8 GB of memory at Q4_K_M (a 6.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 5.4 GB (IQ4_XS) to 39.1 GB (F32).

Dendrite L3 10B iMat is a 9.78B-parameter Dendrite model in GGUF format, quantized by Quant-Cartel. Its trained context length is 8K tokens. The repository has 6 quant files, from 5.4 GB (IQ4_XS) to 39.1 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS5.4 GB 7.2 GB
Tight Get file →
Q4_K_M6.0 GB 7.8 GB
Tight Get file →
Q5_K_M7.0 GB 8.8 GB
Too big Get file →
Q6_K8.0 GB 9.9 GB
Too big Get file →
Q8_010.4 GB 12.2 GB
Too big Get file →
F3239.1 GB 41.0 GB
Too big Get file →

What GPU do you need for Dendrite L3 10B iMat?

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 Q4_K_M (6.0 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.0 GB file, about 9.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (10.4 GB file, about 12.2 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (10.4 GB file, about 12.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (10.4 GB file, about 12.2 GB in use).
  • 48 GB VRAM: the best quant that fits is F32 (39.1 GB file, about 41.0 GB in use).

Which Dendrite L3 10B iMat quant should you choose?

Q4_K_M is the usual starting point for Dendrite L3 10B iMat: it balances file size and quality well. Here it is a 6.0 GB file.

The Q8_0 file is 10.4 GB, about 1.7 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 IQ4_XS at 5.4 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters9.78B
Layers40
Trained context8,192 tokens
KV cache (fp16)160 KB per token

Source

Quantized byQuant-Cartel
FamilyDendrite
Downloads (HF)189
Last updated2024-05-05

Frequently asked questions about Dendrite L3 10B iMat

How much VRAM does Dendrite L3 10B iMat need?

About 7.8 GB at Q4_K_M with an 8K context window. That is the 6.0 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 Dendrite L3 10B iMat on an 8 GB GPU?

Yes, with Q4_K_M: the 6.0 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Dendrite L3 10B iMat GGUF?

It depends on the quant: IQ4_XS is 5.4 GB, Q4_K_M is 6.0 GB, Q5_K_M is 7.0 GB, Q6_K is 8.0 GB, Q8_0 is 10.4 GB, F32 is 39.1 GB.

What context length does Dendrite L3 10B iMat support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.3 GB at 8K and 1.3 GB at 8K.

Where can I download Dendrite L3 10B iMat GGUF?

The files are on Hugging Face in the Quant-Cartel/Dendrite-L3-10B-iMat-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Dendrite L3 10B iMat use?

Hugging Face lists the license as cc-by-nc-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from Quant-Cartel

All by Quant-Cartel →

More Dendrite models

All Dendrite →

Other medium models

All medium models →