FE

Felix 8B

FelixGGUF by ontocordUpdated 2024-03-26
Download on Hugging Face
Parameters8.99B
Context32K
Layers40
Architecturellama
Smallest quant3.4 GB
Quick answer

Felix 8B needs about 7.3 GB of memory at Q4_K_M (a 5.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 9 quants, from 3.4 GB (Q2_K) to 18.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Felix 8B is a 8.99B-parameter Felix model in GGUF format, quantized by ontocord. Its trained context length is 32K tokens. The repository has 9 quant files, from 3.4 GB (Q2_K) to 18.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.4 GB 5.2 GB
Fits Get file →
Q3_K_M4.4 GB 6.2 GB
Fits Get file →
Q4_05.1 GB 6.9 GB
Fits Get file →
Q4_K_M5.4 GB 7.3 GB
Tight Get file →
Q5_06.2 GB 8.0 GB
Too big Get file →
Q5_K_M6.4 GB 8.2 GB
Too big Get file →
Q6_K7.4 GB 9.2 GB
Too big Get file →
Q8_09.6 GB 11.4 GB
Too big Get file →
—18.0 GB 19.8 GB
Too big Get file →

What GPU do you need for Felix 8B?

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 Q2_K (3.4 GB file, about 5.2 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_0 (6.2 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.6 GB file, about 11.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.6 GB file, about 11.4 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (18.0 GB file, about 19.8 GB in use).

Which Felix 8B quant should you choose?

Q4_K_M is the usual starting point for Felix 8B: it balances file size and quality well. Here it is a 5.4 GB file.

The Q8_0 file is 9.6 GB, about 1.8 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 3.4 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
Parameters8.99B
Layers40
Trained context32,768 tokens
KV cache (fp16)160 KB per token

Source

Quantized byontocord
FamilyFelix
Downloads (HF)2
Last updated2024-03-26

Frequently asked questions about Felix 8B

How much VRAM does Felix 8B need?

About 7.3 GB at Q4_K_M with an 8K context window. That is the 5.4 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 Felix 8B on an 8 GB GPU?

Yes, with Q5_0: the 6.2 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Felix 8B GGUF?

It depends on the quant: Q2_K is 3.4 GB, Q3_K_M is 4.4 GB, Q4_0 is 5.1 GB, Q4_K_M is 5.4 GB, Q5_0 is 6.2 GB, Q5_K_M is 6.4 GB and 3 more.

What context length does Felix 8B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Felix 8B GGUF?

The files are on Hugging Face in the ontocord/Felix-8B-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 Felix models

All Felix →

Other small models

All small models →