QW

tungtv qwen f32

QwenGGUF by tungtvUpdated 2024-08-24
Download on Hugging Face
Parameters494M
Context128K
Layers24
Architectureqwen2
Smallest quant2.0 GB
Quick answer

tungtv qwen f32 needs about 2.6 GB of memory at F32 (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.4 GB.

tungtv qwen f32 is a 494M-parameter Qwen model in GGUF format, quantized by tungtv. Its trained context length is 128K tokens. The repository has 1 quant file, from 2.0 GB (F32) to 2.0 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F322.0 GB 2.6 GB
Fits Get file →

What GPU do you need for tungtv qwen f32?

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 F32 (2.0 GB file, about 2.6 GB in use).

Which tungtv qwen f32 quant should you choose?

F32 (2.0 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters494M
Layers24
Trained context131,072 tokens
KV cache (fp16)12 KB per token

Source

Quantized bytungtv
FamilyQwen
Downloads (HF)23
Last updated2024-08-24

Frequently asked questions about tungtv qwen f32

How much VRAM does tungtv qwen f32 need?

About 2.6 GB at F32 with an 8K context window. That is the 2.0 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 tungtv qwen f32 on an 8 GB GPU?

Yes, with F32: the 2.0 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of tungtv qwen f32 GGUF?

It depends on the quant: F32 is 2.0 GB.

What context length does tungtv qwen f32 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.4 GB at 32K.

Where can I download tungtv qwen f32 GGUF?

The files are on Hugging Face in the tungtv/tungtv-qwen-f32-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 tungtv

All by tungtv →

More Qwen models

All Qwen →

Other tiny models

All tiny models →