TinySwallow 1.5B Instruct needs about 1.7 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.6 GB (IQ2_M) to 6.2 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.
TinySwallow 1.5B Instruct – a Japanese instruction‑tuned Qwen2 model
TinySwallow 1.5B Instruct is an instruction‑tuned version of TinySwallow‑1.5B, built with TAID distillation from Qwen2.5‑32B‑Instruct. It is optimized for Japanese language instruction following and conversation.
Good at
- Japanese instruction following
- Tool usage
- Short‑form dialogue
Limits
- No vision support
- Not for commercial deployment
- Requires 8‑k context for estimates
Best for
- Research prototypes
- Japanese chatbots
- Tool‑integrated assistants
Who it’s for. Researchers and developers needing a lightweight Japanese instruction model. Use it for experimentation, not for mission‑critical or commercial applications.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 0.6 GB | 1.3 GB | Fits | Get file → | |
| Q2_K | 0.7 GB | 1.4 GB | Fits | Get file → | |
| IQ3_XS | 0.7 GB | 1.5 GB | Fits | Get file → | |
| Q2_K_L | 0.7 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_S | 0.8 GB | 1.5 GB | Fits | Get file → | |
| IQ3_M | 0.8 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_M | 0.8 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_L | 0.9 GB | 1.6 GB | Fits | Get file → | |
| IQ4_XS | 0.9 GB | 1.6 GB | Fits | Get file → | |
| IQ4_NL | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q3_K_XL | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q4_0 | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q4_K_S | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q4_K_M | 1.0 GB | 1.7 GB | Fits | Get file → | |
| Q4_1 | 1.0 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_L | 1.0 GB | 1.8 GB | Fits | Get file → | |
| Q5_K_S | 1.1 GB | 1.8 GB | Fits | Get file → | |
| Q5_K_M | 1.1 GB | 1.9 GB | Fits | Get file → | |
| Q5_K_L | 1.2 GB | 1.9 GB | Fits | Get file → | |
| Q6_K | 1.3 GB | 2.0 GB | Fits | Get file → | |
| Q6_K_L | 1.3 GB | 2.1 GB | Fits | Get file → | |
| Q8_0 | 1.6 GB | 2.4 GB | Fits | Get file → | |
| F16 | 3.1 GB | 3.8 GB | Fits | Get file → | |
| F32 | 6.2 GB | 6.9 GB | Fits | Get file → |
For 8‑GB VRAM, use IQ2_M (0.6 GB) or Q2_K (0.68 GB). For 16‑GB VRAM, Q4_K_M (0.99 GB) or Q5_K_M (1.13 GB) provide higher quality. For 24‑GB VRAM, Q6_K (1.27 GB) or Q8_0 (1.65 GB) give the best trade‑off.
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 F16 (3.1 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.1 GB file, about 3.8 GB in use).
- 8 GB VRAM: the best quant that fits is F32 (6.2 GB file, about 6.9 GB in use).
Which TinySwallow 1.5B Instruct quant should you choose?
Q4_K_M is the usual starting point for TinySwallow 1.5B Instruct: it balances file size and quality well. Here it is a 1.0 GB file.
The Q8_0 file is 1.6 GB, about 1.7 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 IQ2_M at 0.6 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
Source
Frequently asked questions about TinySwallow 1.5B Instruct
How much VRAM does TinySwallow 1.5B Instruct need?
About 1.7 GB at Q4_K_M with an 8K context window. That is the 1.0 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 TinySwallow 1.5B Instruct on an 8 GB GPU?
Yes, with F32: the 6.2 GB file needs about 6.9 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: IQ2_M is 0.6 GB, Q2_K is 0.7 GB, IQ3_XS is 0.7 GB, Q2_K_L is 0.7 GB, Q3_K_S is 0.8 GB, IQ3_M is 0.8 GB and 18 more.
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 bartowski/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, using IQ2_M or Q2_K quantizations, which are 0.6 GB and 0.68 GB respectively.
Does the model support vision tasks?
No, the model has no vision capabilities.
Is the model suitable for commercial use?
No, it is provided for research and development only and not intended for commercial deployment.