prem 1B SQL needs about 3.0 GB of memory at Q4_K_M (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 14 quants, from 0.6 GB (Q2_K) to 1.4 GB (Q8_0).
Prem 1B SQL – a lightweight Text‑to‑SQL model
Prem 1B SQL is a 1.35B parameter llama‑based model designed for local Text‑to‑SQL tasks. It supports a 16384 token context window and is available in multiple llama.cpp quantizations. The model is released under an MIT license.
Good at
- Local Text‑to‑SQL conversion
- Low‑memory inference
- Customizable prompt formats
Limits
- No vision support
- No external API required
- Requires custom prompt construction
Best for
- Data analysts building local pipelines
- Developers fine‑tuning SQL models
- Security‑sensitive environments
Who it’s for. The model is aimed at developers and data scientists who need a secure, local solution for converting natural language queries into SQL. It is suitable for environments where data privacy and low GPU memory usage are priorities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.6 GB | 2.7 GB | Fits | Get file → | |
| Q3_K_S | 0.6 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_M | 0.7 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_L | 0.7 GB | 2.9 GB | Fits | Get file → | |
| Q4_0 | 0.8 GB | 2.9 GB | Fits | Get file → | |
| Q4_K_S | 0.8 GB | 2.9 GB | Fits | Get file → | |
| Q4_1 | 0.9 GB | 3.0 GB | Fits | Get file → | |
| Q4_K_M | 0.9 GB | 3.0 GB | Fits | Get file → | |
| Q5_0 | 0.9 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_S | 1.0 GB | 3.1 GB | Fits | Get file → | |
| Q5_K_M | 1.0 GB | 3.1 GB | Fits | Get file → | |
| Q5_1 | 1.0 GB | 3.1 GB | Fits | Get file → | |
| Q6_K | 1.2 GB | 3.3 GB | Fits | Get file → | |
| Q8_0 | 1.4 GB | 3.5 GB | Fits | Get file → |
For 8 GB VRAM use Q4_0 (0.78 GB file, ~2.9 GB memory). If 4 GB VRAM is available, Q3_K_S (0.64 GB file, ~2.8 GB memory) is recommended. For CPU‑only inference, Q2_K (0.56 GB file, ~2.7 GB memory) offers the lowest memory footprint.
What GPU do you need for prem 1B SQL?
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 (1.4 GB file, about 3.5 GB in use).
Which prem 1B SQL quant should you choose?
Q4_K_M is the usual starting point for prem 1B SQL: it balances file size and quality well. Here it is a 0.9 GB file.
The Q8_0 file is 1.4 GB, about 1.6 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 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 prem 1B SQL
How much VRAM does prem 1B SQL need?
About 3.0 GB at Q4_K_M with an 8K context window. That is the 0.9 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 prem 1B SQL on an 8 GB GPU?
Yes, with Q8_0: the 1.4 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of prem 1B SQL GGUF?
It depends on the quant: Q2_K is 0.6 GB, Q3_K_S is 0.6 GB, Q3_K_M is 0.7 GB, Q3_K_L is 0.7 GB, Q4_0 is 0.8 GB, Q4_K_S is 0.8 GB and 8 more.
What context length does prem 1B SQL support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.6 GB at 8K and 3.2 GB at 16K.
Where can I download prem 1B SQL GGUF?
The files are on Hugging Face in the QuantFactory/prem-1B-SQL-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Prem 1B SQL on a GPU with 8 GB VRAM?
Yes, the Q4_0 quantization uses about 2.9 GB of VRAM at 8 k context, fitting comfortably on an 8 GB GPU.
What is the smallest quantization that fits on 4 GB VRAM?
The Q3_K_S quantization uses about 2.8 GB of VRAM, which fits on a 4 GB GPU.
Does the model support vision inputs?
No, Prem 1B SQL is a text‑only model and does not process visual data.