LL

chargoddard llama 2 16b nastychat

LlamaGGUF by RichardErkhovUpdated 2024-08-27
Download on Hugging Face
Parameters16.2B
Context4K
Layers—
Architecturellama
Smallest quant2.4 GB
Quick answer

chargoddard llama 2 16b nastychat needs about 3.1 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 2.4 GB (Q4_K_M) to 17.2 GB (Q8_0).

chargoddard llama 2 16b nastychat is a 16.2B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 4K tokens. The repository has 22 quant files, from 2.4 GB (Q4_K_M) to 17.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.4 GB 3.0 GB
Fits Get file →
Q5_K_M3.6 GB 4.3 GB
Fits Get file →
Q2_K6.0 GB 6.9 GB
Fits Get file →
IQ3_XS6.7 GB 7.6 GB
Tight Get file →
IQ3_S7.0 GB 7.9 GB
Tight Get file →
Q3_K_S7.0 GB 7.9 GB
Tight Get file →
IQ3_M7.4 GB 8.4 GB
Too big Get file →
Q3_K7.9 GB 8.8 GB
Too big Get file →
Q3_K_M7.9 GB 8.8 GB
Too big Get file →
Q3_K_L8.6 GB 9.6 GB
Too big Get file →
IQ4_XS8.7 GB 9.7 GB
Too big Get file →
Q4_09.2 GB 10.2 GB
Too big Get file →
IQ4_NL9.2 GB 10.3 GB
Too big Get file →
Q4_K_S9.2 GB 10.3 GB
Too big Get file →
Q4_K9.8 GB 10.9 GB
Too big Get file →
Q4_110.2 GB 11.3 GB
Too big Get file →
Q5_011.2 GB 12.3 GB
Too big Get file →
Q5_K_S11.2 GB 12.3 GB
Too big Get file →
Q5_K11.5 GB 12.7 GB
Too big Get file →
Q5_112.2 GB 13.4 GB
Too big Get file →
Q6_K13.3 GB 14.6 GB
Too big Get file →
Q8_017.2 GB 18.7 GB
Too big Get file →

What GPU do you need for chargoddard llama 2 16b nastychat?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q4_K_M (2.4 GB file, about 3.1 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_K_M (3.6 GB file, about 4.5 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_XS (6.7 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_1 (10.2 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (13.3 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (17.2 GB file, about 19.8 GB in use).

Which chargoddard llama 2 16b nastychat quant should you choose?

Q4_K_M is the usual starting point for chargoddard llama 2 16b nastychat: it balances file size and quality well. Here it is a 2.4 GB file.

The Q8_0 file is 17.2 GB, about 7.3 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters16.2B
Trained context4,096 tokens

Source

Quantized byRichardErkhov
FamilyLlama
Downloads (HF)168
Last updated2024-08-27

Frequently asked questions about chargoddard llama 2 16b nastychat

How much VRAM does chargoddard llama 2 16b nastychat need?

About 3.1 GB at Q4_K_M with an 8K context window. That is the 2.4 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 chargoddard llama 2 16b nastychat on an 8 GB GPU?

Yes, with IQ3_XS: the 6.7 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 chargoddard llama 2 16b nastychat GGUF?

It depends on the quant: Q4_K_M is 2.4 GB, Q5_K_M is 3.6 GB, Q2_K is 6.0 GB, IQ3_XS is 6.7 GB, IQ3_S is 7.0 GB, Q3_K_S is 7.0 GB and 16 more.

What context length does chargoddard llama 2 16b nastychat support?

The GGUF header lists a trained context length of 4,096 tokens (4K).

Where can I download chargoddard llama 2 16b nastychat GGUF?

The files are on Hugging Face in the RichardErkhov/chargoddard_-_llama-2-16b-nastychat-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 RichardErkhov

All by RichardErkhov →

More Llama models

All Llama →

Other medium models

All medium models →