QW

Hercules-5.0-Qwen2-1.5B

QwenGGUF by bartowskiUpdated 2024-06-12
Download on Hugging Face
Parameters1.54B
Context128K
Layers28
Architectureqwen2
Smallest quant0.8 GB
Quick answer

Hercules-5.0-Qwen2-1.5B needs about 1.7 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 10 quants, from 0.8 GB (IQ3_M) to 6.2 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

Hercules-5.0-Qwen2-1.5B is a 1.54B-parameter Qwen model in GGUF format, quantized by bartowski. Its trained context length is 128K tokens. The repository has 10 quant files, from 0.8 GB (IQ3_M) to 6.2 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_M0.8 GB 1.5 GB
Fits Get file →
Q3_K_L0.9 GB 1.6 GB
Fits Get file →
IQ4_XS0.9 GB 1.6 GB
Fits Get file →
Q4_K_S0.9 GB 1.7 GB
Fits Get file →
Q4_K_M1.0 GB 1.7 GB
Fits Get file →
Q5_K_S1.1 GB 1.8 GB
Fits Get file →
Q5_K_M1.1 GB 1.9 GB
Fits Get file →
Q6_K1.3 GB 2.0 GB
Fits Get file →
Q8_01.6 GB 2.4 GB
Fits Get file →
F326.2 GB 6.9 GB
Fits Get file →

What GPU do you need for Hercules-5.0-Qwen2-1.5B?

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 Q8_0 (1.6 GB file, about 2.4 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (1.6 GB file, about 2.4 GB in use).
  • 8 GB VRAM: the best quant that fits is F32 (6.2 GB file, about 6.9 GB in use).

Which Hercules-5.0-Qwen2-1.5B quant should you choose?

Q4_K_M is the usual starting point for Hercules-5.0-Qwen2-1.5B: it balances file size and quality well. Here it is a 1.0 GB file.

The Q8_0 file is 1.6 GB, about 1.7 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 IQ3_M at 0.8 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

Architectureqwen2
Parameters1.54B
Layers28
Trained context131,072 tokens
KV cache (fp16)28 KB per token

Source

Quantized bybartowski
FamilyQwen
Licenseapache-2.0
Downloads (HF)252
Last updated2024-06-12

Frequently asked questions about Hercules-5.0-Qwen2-1.5B

How much VRAM does Hercules-5.0-Qwen2-1.5B need?

About 1.7 GB at Q4_K_M with an 8K context window. That is the 1.0 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 Hercules-5.0-Qwen2-1.5B on an 8 GB GPU?

Yes, with F32: the 6.2 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Hercules-5.0-Qwen2-1.5B GGUF?

It depends on the quant: IQ3_M is 0.8 GB, Q3_K_L is 0.9 GB, IQ4_XS is 0.9 GB, Q4_K_S is 0.9 GB, Q4_K_M is 1.0 GB, Q5_K_S is 1.1 GB and 4 more.

What context length does Hercules-5.0-Qwen2-1.5B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download Hercules-5.0-Qwen2-1.5B GGUF?

The files are on Hugging Face in the bartowski/Hercules-5.0-Qwen2-1.5B-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 Hercules-5.0-Qwen2-1.5B use?

Hugging Face lists the license as apache-2.0. 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 bartowski

All by bartowski →

More Qwen models

All Qwen →

Other tiny models

All tiny models →