QW

TinySwallow 1.5B Instruct

QwenGGUF by SakanaAIUpdated 2025-01-30
Download on Hugging Face
Parameters1.54B
Context32K
Layers28
Architectureqwen2
Smallest quant1.1 GB
Quick answer

TinySwallow 1.5B Instruct needs about 1.9 GB of memory at Q5_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.1 GB (Q5_K_M) to 1.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

TinySwallow 1.5B Instruct – a compact, instruction‑tuned Qwen2.5 model

TinySwallow 1.5B Instruct is a 1.54B‑parameter autoregressive language model based on Qwen2.5. It supports up to 32,768 context tokens and 8,192 generation tokens. The model is instruction‑tuned and optimized for Japanese conversation.

Good at

  • Instruction following
  • Japanese language support
  • Long‑context generation

Limits

  • No vision support
  • Not for commercial deployment
  • Requires Apache‑2.0 license

Best for

  • Chatbot prototypes
  • Japanese text generation
  • Research experiments

Who it’s for. Developers and researchers who need a lightweight, instruction‑tuned Japanese LLM for experimentation or prototyping. The model is not intended for production or mission‑critical use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M1.1 GB 1.9 GB
Fits Get file →
Q8_01.6 GB 2.4 GB
Fits Get file →

For 8 GB VRAM, use Q5_K_M (1.13 GB file, ~1.9 GB memory at 8K context). For 12 GB VRAM, Q8_0 (1.65 GB file, ~2.4 GB memory at 8K context) is suitable. Memory estimates are approximate.

What GPU do you need for TinySwallow 1.5B Instruct?

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).

Which TinySwallow 1.5B Instruct quant should you choose?

Q5_K_M (1.1 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters1.54B
Layers28
Trained context32,768 tokens
KV cache (fp16)28 KB per token

Source

Quantized bySakanaAI
FamilyQwen
Licenseapache-2.0
Downloads (HF)2,069
Last updated2025-01-30

Frequently asked questions about TinySwallow 1.5B Instruct

How much VRAM does TinySwallow 1.5B Instruct need?

About 1.9 GB at Q5_K_M with an 8K context window. That is the 1.1 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 TinySwallow 1.5B Instruct on an 8 GB GPU?

Yes, with Q8_0: the 1.6 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of TinySwallow 1.5B Instruct GGUF?

It depends on the quant: Q5_K_M is 1.1 GB, Q8_0 is 1.6 GB.

What context length does TinySwallow 1.5B Instruct support?

The GGUF header lists a trained context length of 32,768 tokens (32K). 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 TinySwallow 1.5B Instruct GGUF?

The files are on Hugging Face in the SakanaAI/TinySwallow-1.5B-Instruct-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 TinySwallow 1.5B Instruct 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.

Can I run TinySwallow 1.5B Instruct on 8 GB VRAM?

Yes, the Q5_K_M quantization uses about 1.9 GB of VRAM at 8K context, fitting within an 8 GB GPU.

Does the model support images?

No, TinySwallow 1.5B Instruct is a text‑only model with no vision capabilities.

Is this model suitable for commercial deployment?

No, the model is provided for research and development only and is not intended for commercial or mission‑critical use.

Other GGUFs of Qwen2.5-1.5B-Instruct

Similar models

Browse all →

More Qwen models

All Qwen →

Other tiny models

All tiny models →