BA

Basilisk 4B

BasiliskGGUF by AryanneUpdated 2023-10-05
Download on Hugging Face
Parameters3.5B
Context4K
Layers16
Architecturellama
Smallest quant1.5 GB
Quick answer

Basilisk 4B needs about 4.8 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 7 quants, from 1.5 GB (Q2_K) to 2.4 GB (Q5_0).

Basilisk 4B – a 4B parameter Llama‑2 model finetuned with open orca CoT data

Basilisk 4B is a 4B parameter Llama‑2 model finetuned on open orca CoT data. It supports a 4096 token context window and is available in several GGUF quantizations. The model is hosted on Hugging Face and can be run with llama.cpp.

Good at

  • Fine‑tuned CoT reasoning
  • Compact quantizations
  • Llama‑2 architecture

Limits

  • No vision support
  • License not specified
  • Context limited to 4096 tokens

Best for

  • Chatbot prototypes
  • CoT task demos
  • Low‑memory inference

Who it’s for. Developers and researchers who need a small Llama‑2 variant for reasoning tasks and want to experiment with different GGUF quantizations. The model is suitable for local deployment on modest hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.5 GB 3.1 GB
Fits Get file →
Q2_K1.5 GB 3.1 GB
Fits Get file →
Q4_02.0 GB 3.6 GB
Fits Get file →
Q4_02.0 GB 3.6 GB
Fits Get file →
Q4_K_M2.1 GB 3.7 GB
Fits Get file →
Q5_02.4 GB 4.0 GB
Fits Get file →
Q5_02.4 GB 4.0 GB
Fits Get file →

For 8 GB VRAM, use Q4_0 (2 GB file, ~4.7 GB RAM). For 6 GB VRAM, Q2_K (1.49 GB file, ~4.1 GB RAM) is a good choice. If memory allows, Q5_0 (2.43 GB file, ~5.1 GB RAM) offers higher quality.

What GPU do you need for Basilisk 4B?

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 Q5_0 (2.4 GB file, about 5.1 GB in use).

Which Basilisk 4B quant should you choose?

Q4_K_M is the usual starting point for Basilisk 4B: it balances file size and quality well. Here it is a 2.1 GB file.

If memory is tight, the smallest file is Q2_K at 1.5 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
Parameters3.5B
Layers16
Trained context4,096 tokens
KV cache (fp16)256 KB per token

Source

Quantized byAryanne
FamilyBasilisk
Downloads (HF)517
Last updated2023-10-05

Frequently asked questions about Basilisk 4B

How much VRAM does Basilisk 4B need?

About 4.8 GB at Q4_K_M with an 8K context window. That is the 2.1 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 Basilisk 4B on an 8 GB GPU?

Yes, with Q5_0: the 2.4 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Basilisk 4B GGUF?

It depends on the quant: Q2_K is 1.5 GB, Q2_K is 1.5 GB, Q4_0 is 2.0 GB, Q4_0 is 2.0 GB, Q4_K_M is 2.1 GB, Q5_0 is 2.4 GB and 1 more.

What context length does Basilisk 4B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.1 GB at 8K and 1.1 GB at 4K.

Where can I download Basilisk 4B GGUF?

The files are on Hugging Face in the Aryanne/Basilisk-4B-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Basilisk 4B on 8 GB VRAM?

Yes, the Q4_0 quantization requires about 4.7 GB of RAM at 8k context, which fits within 8 GB VRAM.

Does Basilisk 4B support vision?

No, the model has no vision capabilities.

Similar models

Browse all →

More from Aryanne

All by Aryanne →

More Basilisk models

All Basilisk →

Other tiny models

All tiny models →