GP

gpt2-xl-conversational

GptGGUF by RichardErkhovUpdated 2024-05-03
Download on Hugging Face
Parameters1.64B
Context1K
Layers48
Architecturegpt2
Smallest quant0.9 GB
Quick answer

gpt2-xl-conversational needs about 4.2 GB of memory at Q4_K_M (a 1.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 21 quants, from 0.9 GB (IQ3_S) to 1.6 GB (Q6_K).

gpt2-xl-conversational is a 1.64B-parameter Gpt model in GGUF format, quantized by RichardErkhov. Its trained context length is 1K tokens. The repository has 21 quant files, from 0.9 GB (IQ3_S) to 1.6 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_S0.9 GB 1.7 GB
Fits Get file →
IQ3_XS0.9 GB 1.7 GB
Fits Get file →
Q2_K0.9 GB 1.7 GB
Fits Get file →
Q3_K_S0.9 GB 1.7 GB
Fits Get file →
IQ4_XS1.0 GB 1.8 GB
Fits Get file →
Q4_01.0 GB 1.8 GB
Fits Get file →
IQ3_M1.0 GB 1.8 GB
Fits Get file →
IQ4_NL1.0 GB 1.8 GB
Fits Get file →
Q3_K1.0 GB 1.8 GB
Fits Get file →
Q3_K_M1.0 GB 1.8 GB
Fits Get file →
Q4_11.1 GB 1.9 GB
Fits Get file →
Q3_K_L1.1 GB 1.9 GB
Fits Get file →
Q4_K_S1.1 GB 1.9 GB
Fits Get file →
Q5_01.2 GB 2.0 GB
Fits Get file →
Q4_K1.2 GB 2.0 GB
Fits Get file →
Q4_K_M1.2 GB 2.0 GB
Fits Get file →
Q5_K_S1.2 GB 2.0 GB
Fits Get file →
Q5_11.3 GB 2.1 GB
Fits Get file →
Q5_K1.4 GB 2.2 GB
Fits Get file →
Q5_K_M1.4 GB 2.2 GB
Fits Get file →
Q6_K1.6 GB 2.4 GB
Fits Get file →

What GPU do you need for gpt2-xl-conversational?

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: the best quant that fits is IQ4_NL (1.0 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (1.6 GB file, about 4.6 GB in use).

Which gpt2-xl-conversational quant should you choose?

Q4_K_M is the usual starting point for gpt2-xl-conversational: it balances file size and quality well. Here it is a 1.2 GB file.

If memory is tight, the smallest file is IQ3_S at 0.9 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt2
Parameters1.64B
Layers48
Trained context1,024 tokens
KV cache (fp16)300 KB per token

Source

Quantized byRichardErkhov
FamilyGpt
Downloads (HF)251
Last updated2024-05-03

Frequently asked questions about gpt2-xl-conversational

How much VRAM does gpt2-xl-conversational need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 1.2 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 gpt2-xl-conversational on an 8 GB GPU?

Yes, with Q6_K: the 1.6 GB file needs about 4.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gpt2-xl-conversational GGUF?

It depends on the quant: IQ3_S is 0.9 GB, IQ3_XS is 0.9 GB, Q2_K is 0.9 GB, Q3_K_S is 0.9 GB, IQ4_XS is 1.0 GB, Q4_0 is 1.0 GB and 15 more.

What context length does gpt2-xl-conversational support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 2.5 GB at 8K and 0.3 GB at 1K.

Where can I download gpt2-xl-conversational GGUF?

The files are on Hugging Face in the RichardErkhov/Locutusque_-_gpt2-xl-conversational-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 Gpt models

All Gpt →

Other tiny models

All tiny models →