XiYanSQL QwenCoder 3B 2504 needs about 2.7 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.3 GB (Q2_K) to 6.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.
XiYanSQL QwenCoder 3B 2504 – a 3.09B parameter SQL generation model
XiYanSQL QwenCoder 3B 2504 is a 3.09B parameter model trained on 32768 context tokens. It specializes in coding and tool usage, with strong multi‑dialect SQL generation capabilities. The model is released under the apache-2.0 license.
Good at
- SQL generation across PostgreSQL and MySQL dialects
- Multi‑dialect support
- Tool‑aware code generation
Limits
- No vision support
- Requires 8k context for estimates
- License is apache-2.0
Best for
- Generating complex SQL queries
- Automating database interactions
- Developing SQL‑centric tools
Who it’s for. Developers and data engineers needing accurate SQL generation in multiple dialects. The model is suitable for integration into applications that require code‑aware language models.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.3 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_S | 1.5 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_M | 1.6 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_L | 1.7 GB | 2.5 GB | Fits | Get file → | |
| IQ4_XS | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_S | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_M | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_S | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q6_K | 2.5 GB | 3.3 GB | Fits | Get file → | |
| Q8_0 | 3.3 GB | 4.1 GB | Fits | Get file → | |
| F16 | 6.2 GB | 7.0 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 1.93 GB, estimated memory 2.7 GB). If 4 GB VRAM is available, Q3_K_M (1.59 GB, 2.4 GB). For higher precision, Q5_K_M (2.22 GB, 3 GB) can be used on systems with 8 GB VRAM.
What GPU do you need for XiYanSQL QwenCoder 3B 2504?
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 Q6_K (2.5 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.1 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (6.2 GB file, about 7.0 GB in use).
Which XiYanSQL QwenCoder 3B 2504 quant should you choose?
Q4_K_M is the usual starting point for XiYanSQL QwenCoder 3B 2504: it balances file size and quality well. Here it is a 1.9 GB file.
The Q8_0 file is 3.3 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 Q2_K at 1.3 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
Frequently asked questions about XiYanSQL QwenCoder 3B 2504
How much VRAM does XiYanSQL QwenCoder 3B 2504 need?
About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.9 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 XiYanSQL QwenCoder 3B 2504 on an 8 GB GPU?
Yes, with F16: the 6.2 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of XiYanSQL QwenCoder 3B 2504 GGUF?
It depends on the quant: Q2_K is 1.3 GB, Q3_K_S is 1.5 GB, Q3_K_M is 1.6 GB, Q3_K_L is 1.7 GB, IQ4_XS is 1.8 GB, Q4_K_S is 1.8 GB and 6 more.
What context length does XiYanSQL QwenCoder 3B 2504 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.
Where can I download XiYanSQL QwenCoder 3B 2504 GGUF?
The files are on Hugging Face in the mradermacher/XiYanSQL-QwenCoder-3B-2504-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 XiYanSQL QwenCoder 3B 2504 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 XiYanSQL QwenCoder 3B 2504 on 8 GB VRAM?
Yes, use the Q4_K_M quant which requires approximately 2.7 GB of VRAM at 8k context.
Does the model support image inputs?
No, the model does not have vision capabilities.
What license does the model use?
The model is released under the apache-2.0 license.