CL

Clover3 17B

CloverGGUF by Undi95Updated 2023-12-12
Download on Hugging Face
Parameters16.8B
Context32K
Layers76
Architecturellama
Smallest quant9.5 GB
Quick answer

Clover3 17B needs about 15.0 GB of memory at Q5_K_M (a 11.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 9.5 GB (Q4_K_S) to 17.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.2 GB.

Clover3 17B is a 16.8B-parameter Clover model in GGUF format, quantized by Undi95. Its trained context length is 32K tokens. The repository has 4 quant files, from 9.5 GB (Q4_K_S) to 17.9 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S9.5 GB 12.6 GB
Too big Get file →
Q5_K_M11.9 GB 15.0 GB
Too big Get file →
Q6_K13.8 GB 16.9 GB
Too big Get file →
Q8_017.9 GB 20.9 GB
Too big Get file →

What GPU do you need for Clover3 17B?

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: the best quant that fits is Q5_K_M (11.9 GB file, about 15.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (17.9 GB file, about 20.9 GB in use).

Which Clover3 17B quant should you choose?

Q5_K_M (11.9 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 Q4_K_S at 9.5 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
Parameters16.8B
Layers76
Trained context32,768 tokens
KV cache (fp16)304 KB per token

Source

Quantized byUndi95
FamilyClover
Downloads (HF)42
Last updated2023-12-12

Frequently asked questions about Clover3 17B

How much VRAM does Clover3 17B need?

About 15.0 GB at Q5_K_M with an 8K context window. That is the 11.9 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 Clover3 17B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Clover3 17B GGUF?

It depends on the quant: Q4_K_S is 9.5 GB, Q5_K_M is 11.9 GB, Q6_K is 13.8 GB, Q8_0 is 17.9 GB.

What context length does Clover3 17B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.6 GB at 8K and 10.2 GB at 32K.

Where can I download Clover3 17B GGUF?

The files are on Hugging Face in the Undi95/Clover3-17B-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 Clover3 17B 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 Undi95

All by Undi95 →

More Clover models

All Clover →

Other medium models

All medium models →