QW

bling qwen 1.5b FP16

QwenGGUF by ApprikatAIUpdated 2024-10-14
Download on Hugging Face
Parameters1.78B
Context128K
Layers28
Architectureqwen2
Smallest quant3.6 GB
Quick answer

bling qwen 1.5b FP16 needs about 4.3 GB of memory at its main file (a 3.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

bling qwen 1.5b FP16 is a 1.78B-parameter Qwen model in GGUF format, quantized by ApprikatAI. Its trained context length is 128K tokens. The repository has 1 quant file, from 3.6 GB to 3.6 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—3.6 GB 4.3 GB
Fits Get file →

What GPU do you need for bling qwen 1.5b FP16?

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 the main file (3.6 GB file, about 4.3 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters1.78B
Layers28
Trained context131,072 tokens
KV cache (fp16)28 KB per token

Source

Quantized byApprikatAI
FamilyQwen
Licenseapache-2.0
Downloads (HF)23
Last updated2024-10-14

Frequently asked questions about bling qwen 1.5b FP16

How much VRAM does bling qwen 1.5b FP16 need?

About 4.3 GB at its main file with an 8K context window. That is the 3.6 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 bling qwen 1.5b FP16 on an 8 GB GPU?

Yes, with the smaller files: the 3.6 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of bling qwen 1.5b FP16 GGUF?

It depends on the quant: file is 3.6 GB.

What context length does bling qwen 1.5b FP16 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 bling qwen 1.5b FP16 GGUF?

The files are on Hugging Face in the ApprikatAI/bling-qwen-1.5b-FP16-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 bling qwen 1.5b FP16 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.

Other GGUFs of bling-qwen-1.5b

Similar models

Browse all →

More from ApprikatAI

All by ApprikatAI →

More Qwen models

All Qwen →

Other tiny models

All tiny models →