sqlcoder 7b 2 needs about 9.6 GB of memory at Q5_K_M (a 4.8 GB file) with an 8K context window, so it fits on a 12 GB GPU.
SQLCoder‑7B‑2: a 7B LLaMA‑based model for natural‑language to SQL conversion
SQLCoder‑7B‑2 is a 7 billion‑parameter LLaMA model fine‑tuned for translating natural language queries into SQL. It was updated on 7 Feb 2024 and is optimized for join operations. The model is released under CC‑BY‑SA‑4.0.
Good at
- SQL generation from plain text
- Optimized join handling
- Read‑only database analytics
Limits
- Requires 8 k context for full performance
- Only text‑to‑SQL, no vision
- License allows redistribution but requires attribution
Best for
- Generating SQL queries from user questions
- Automating data analysis for non‑technical staff
- Creating read‑only database reports
Who it’s for. Developers and analysts who need quick SQL from natural language. It is suitable for read‑only database environments and non‑technical users seeking analytics tools.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 4.8 GB | 9.6 GB | Too big | Get file → |
The Q5_K_M quant is 4.78 GB and needs about 9.6 GB of VRAM at 8 k context. For 8 GB VRAM, use Q5_K_M; for 12 GB VRAM, a higher‑precision quant would be possible but is not listed.
What GPU do you need for sqlcoder 7b 2?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q5_K_M (4.8 GB file, about 9.6 GB in use).
Which sqlcoder 7b 2 quant should you choose?
Q5_K_M (4.8 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
Source
Frequently asked questions about sqlcoder 7b 2
How much VRAM does sqlcoder 7b 2 need?
About 9.6 GB at Q5_K_M with an 8K context window. That is the 4.8 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 sqlcoder 7b 2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of sqlcoder 7b 2 GGUF?
It depends on the quant: Q5_K_M is 4.8 GB.
What context length does sqlcoder 7b 2 support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 4.3 GB at 8K and 8.6 GB at 16K.
Where can I download sqlcoder 7b 2 GGUF?
The files are on Hugging Face in the defog/sqlcoder-7b-2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does sqlcoder 7b 2 use?
Hugging Face lists the license as cc-by-sa-4.0. 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 SQLCoder‑7B‑2 on 8 GB VRAM?
Yes, the Q5_K_M quant uses roughly 9.6 GB of VRAM at 8 k context, which fits within an 8 GB GPU with some headroom.
Does SQLCoder‑7B‑2 support image inputs?
No, the model only handles text input and does not include vision capabilities.
What license applies to SQLCoder‑7B‑2?
It is released under CC‑BY‑SA‑4.0, requiring attribution and share‑alike for derivative works.