SQ

OG SQL 7B

SqlGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters6.74B
Context16K
Layers32
Architecturellama
Smallest quant2.5 GB
Quick answer

OG SQL 7B needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 2.5 GB (Q2_K) to 7.2 GB (Q8_0).

OG SQL 7B – a transformer fine‑tuned to convert natural language into SQL queries

OG SQL 7B is a 6.74 billion‑parameter model based on OneGate/OG‑SQL‑7B. It was trained to translate natural language into SQL commands. The model supports a 16384‑token context window and is released under cc‑by‑4.0.

Good at

  • Translating natural language to SQL
  • Handling long context up to 16384 tokens
  • Fine‑tuned for database query generation

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • License is cc‑by‑4.0 – requires attribution

Best for

  • Automated database querying
  • SQL learning tools
  • Chatbot back‑ends for data access

Who it’s for. Developers and data analysts who need quick conversion of plain‑English queries into SQL. The model is suitable for integration into applications that require natural‑language database access.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.5 GB 7.3 GB
Tight Get file →
IQ3_XS2.8 GB 7.6 GB
Tight Get file →
IQ3_S2.9 GB 7.7 GB
Tight Get file →
Q3_K_S2.9 GB 7.7 GB
Tight Get file →
IQ3_M3.1 GB 7.9 GB
Tight Get file →
Q3_K_M3.3 GB 8.1 GB
Too big Get file →
Q3_K_L3.6 GB 8.4 GB
Too big Get file →
IQ4_XS3.6 GB 8.4 GB
Too big Get file →
Q4_K_S3.9 GB 8.7 GB
Too big Get file →
Q4_K_M4.1 GB 8.9 GB
Too big Get file →
Q5_K_S4.7 GB 9.4 GB
Too big Get file →
Q5_K_M4.8 GB 9.6 GB
Too big Get file →
Q6_K5.5 GB 10.3 GB
Too big Get file →
Q8_07.2 GB 12.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (est. 8.7 GB) or Q3_K_M (est. 8.1 GB). For 12 GB VRAM, Q4_K_M (est. 8.9 GB) or Q5_K_S (est. 9.4 GB) are suitable. Larger models like Q6_K need 10.3 GB memory and Q8_0 needs 12 GB.

What GPU do you need for OG SQL 7B?

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: the best quant that fits is IQ3_M (3.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).

Which OG SQL 7B quant should you choose?

Q4_K_M is the usual starting point for OG SQL 7B: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 GB, about 1.8 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 2.5 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

Architecturellama
Parameters6.74B
Layers32
Trained context16,384 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilySql
Licensecc-by-4.0
Downloads (HF)2,043
Last updated2024-05-06

Frequently asked questions about OG SQL 7B

How much VRAM does OG SQL 7B need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 OG SQL 7B on an 8 GB GPU?

Yes, with IQ3_M: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of OG SQL 7B GGUF?

It depends on the quant: Q2_K is 2.5 GB, IQ3_XS is 2.8 GB, IQ3_S is 2.9 GB, Q3_K_S is 2.9 GB, IQ3_M is 3.1 GB, Q3_K_M is 3.3 GB and 8 more.

What context length does OG SQL 7B 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 OG SQL 7B GGUF?

The files are on Hugging Face in the mradermacher/OG-SQL-7B-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 OG SQL 7B use?

Hugging Face lists the license as cc-by-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 OG SQL 7B on 8 GB VRAM?

Yes, with the Q4_K_S or Q3_K_M quant, which estimate 8.7 GB or 8.1 GB memory at 8k context.

Does OG SQL 7B support image input?

No, the model has no vision capabilities.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Sql models

All Sql →

Other small models

All small models →