QW

Qwen1.5 1.8B Layla v4

QwenGGUF by l3utterflyUpdated 2024-08-20
Download on Hugging Face
Parameters1.84B
Context32K
Layers24
Architectureqwen2
Smallest quant0.8 GB
Quick answer

Qwen1.5 1.8B Layla v4 needs about 3.3 GB of memory at Q4_K_M (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 10 quants, from 0.8 GB (Q2_K) to 3.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Qwen1.5 1.8B Layla v4 is a 1.84B-parameter Qwen model in GGUF format, quantized by l3utterfly. Its trained context length is 32K tokens. The repository has 10 quant files, from 0.8 GB (Q2_K) to 3.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.8 GB 3.0 GB
Fits Get file →
Q4_01.1 GB 3.2 GB
Fits Get file →
Q4_01.1 GB 3.2 GB
Fits Get file →
Q4_01.1 GB 3.2 GB
Fits Get file →
Q4_K1.2 GB 3.3 GB
Fits Get file →
Q4_K_M1.2 GB 3.3 GB
Fits Get file →
Q5_K1.4 GB 3.5 GB
Fits Get file →
Q6_K1.6 GB 3.7 GB
Fits Get file →
Q8_02.0 GB 4.1 GB
Fits Get file →
F163.7 GB 5.8 GB
Fits Get file →

What GPU do you need for Qwen1.5 1.8B Layla v4?

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 Q6_K (1.6 GB file, about 3.7 GB in use).
  • 6 GB VRAM: the best quant that fits is F16 (3.7 GB file, about 5.8 GB in use).

Which Qwen1.5 1.8B Layla v4 quant should you choose?

Q4_K_M is the usual starting point for Qwen1.5 1.8B Layla v4: it balances file size and quality well. Here it is a 1.2 GB file.

The Q8_0 file is 2.0 GB, about 1.6 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 0.8 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

Architectureqwen2
Parameters1.84B
Layers24
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized byl3utterfly
FamilyQwen
Licenseapache-2.0
Downloads (HF)551
Last updated2024-08-20

Frequently asked questions about Qwen1.5 1.8B Layla v4

How much VRAM does Qwen1.5 1.8B Layla v4 need?

About 3.3 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 Qwen1.5 1.8B Layla v4 on an 8 GB GPU?

Yes, with F16: the 3.7 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen1.5 1.8B Layla v4 GGUF?

It depends on the quant: Q2_K is 0.8 GB, Q4_0 is 1.1 GB, Q4_0 is 1.1 GB, Q4_0 is 1.1 GB, Q4_K is 1.2 GB, Q4_K_M is 1.2 GB and 4 more.

What context length does Qwen1.5 1.8B Layla v4 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download Qwen1.5 1.8B Layla v4 GGUF?

The files are on Hugging Face in the l3utterfly/Qwen1.5-1.8B-layla-v4-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 Qwen1.5 1.8B Layla v4 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 l3utterfly

All by l3utterfly →

More Qwen models

All Qwen →

Other tiny models

All tiny models →