QW

Sakura 1.5B Qwen2.5 v1.0 GGUF IMX

QwenGGUF by shing3232Updated 2024-11-08
Download on Hugging Face
Parameters1.78B
Context128K
Layers28
Architectureqwen2
Smallest quant1.3 GB
Quick answer

Sakura 1.5B Qwen2.5 v1.0 GGUF IMX needs about 2.0 GB of memory at its main file (a 1.3 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 0.9 GB.

Sakura 1.5B Qwen2.5 v1.0 GGUF IMX – a compact Qwen model

Sakura 1.5B Qwen2.5 v1.0 is a 1.8‑billion‑parameter model based on the Qwen2 architecture. It is available in a single GGUF file of 1.26 GB and supports a context length of up to 131 072 tokens.

Good at

  • Large context handling
  • Compact size for low‑resource setups
  • Qwen2 architecture compatibility

Limits

  • No license information provided
  • No vision or multimodal support
  • Single quantization available

Best for

  • Chatbots needing long context
  • Local inference on modest GPUs
  • Educational demos of Qwen models

Who it’s for. Developers and researchers who require a small Qwen model with extended context capability. The model is suitable for local deployment where GPU memory is limited.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.3 GB 2.0 GB
Fits Get file →

The only available quant is the default GGUF file, 1.26 GB. It requires approximately 2 GB of VRAM at 8 k context. For 4 GB VRAM, it fits comfortably. No other quants are listed, so use this file for all memory budgets.

What GPU do you need for Sakura 1.5B Qwen2.5 v1.0 GGUF IMX?

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 the main file (1.3 GB file, about 2.0 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 byshing3232
FamilyQwen
Downloads (HF)10,901
Last updated2024-11-08

Frequently asked questions about Sakura 1.5B Qwen2.5 v1.0 GGUF IMX

How much VRAM does Sakura 1.5B Qwen2.5 v1.0 GGUF IMX need?

About 2.0 GB at its main file with an 8K context window. That is the 1.3 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 Sakura 1.5B Qwen2.5 v1.0 GGUF IMX on an 8 GB GPU?

Yes, with the smaller files: the 1.3 GB file needs about 2.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sakura 1.5B Qwen2.5 v1.0 GGUF IMX GGUF?

It depends on the quant: file is 1.3 GB.

What context length does Sakura 1.5B Qwen2.5 v1.0 GGUF IMX 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 Sakura 1.5B Qwen2.5 v1.0 GGUF IMX GGUF?

The files are on Hugging Face in the shing3232/Sakura-1.5B-Qwen2.5-v1.0-GGUF-IMX repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Sakura 1.5B on 4 GB VRAM?

Yes, the 1.26 GB GGUF file needs about 2 GB of VRAM at 8 k context, so 4 GB is sufficient.

Does this model support vision tasks?

No, the model has no vision or multimodal capabilities.

What is the maximum context length?

The model supports up to 131 072 tokens of context.

Similar models

Browse all →

More from shing3232

All by shing3232 →

More Qwen models

All Qwen →

Other tiny models

All tiny models →