SQ

defog_sqlcoder-34b-alpha

SqlcoderGGUF by TheBlokeUpdated 2023-11-18
Download on Hugging Face
Parameters33.7B
Context16K
Layers48
Architecturellama
Smallest quant14.2 GB
Quick answer

defog_sqlcoder-34b-alpha needs about 22.3 GB of memory at Q4_K_M (a 20.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 12 quants, from 14.2 GB (Q2_K) to 35.9 GB (Q8_0).

Defog SQLCoder-34B Alpha – 33.7B parameter LLM for SQL generation

Defog SQLCoder-34B Alpha is a 33.7B parameter model fine‑tuned on CodeLlama for converting natural language to SQL queries. It is available in GGUF format and supports a 16384 token context window. The model is licensed under CC‑BY‑4.0.

Good at

  • Natural language to SQL conversion
  • SQL query generation
  • Code generation

Limits

  • No vision support
  • Requires 20GB+ VRAM for 8‑bit/4‑bit quant
  • Large memory footprint for higher precision

Best for

  • Building SQL query assistants
  • Automating database queries
  • Developing code generation tools

Who it’s for. Engineers and data scientists needing accurate SQL generation from plain language. The model is suitable for developers building chatbots or tools that translate user queries into database commands.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K14.2 GB 16.3 GB
Too big Get file →
Q3_K_S14.6 GB 16.7 GB
Too big Get file →
Q3_K_M16.3 GB 18.4 GB
Too big Get file →
Q3_K_L17.8 GB 19.9 GB
Too big Get file →
Q4_019.1 GB 21.2 GB
Too big Get file →
Q4_K_S19.1 GB 21.3 GB
Too big Get file →
Q4_K_M20.2 GB 22.3 GB
Too big Get file →
Q5_023.2 GB 25.3 GB
Too big Get file →
Q5_K_S23.2 GB 25.3 GB
Too big Get file →
Q5_K_M23.8 GB 26.0 GB
Too big Get file →
Q6_K27.7 GB 29.8 GB
Too big Get file →
Q8_035.9 GB 38.0 GB
Too big Get file →

For 20GB VRAM, use Q4_0 (19.05 GB file, 21.2 GB memory) or Q4_K_S (19.15 GB file, 21.3 GB memory). For 8GB VRAM, use Q2_K (14.21 GB file, 16.3 GB memory) or Q3_K_S (14.61 GB file, 16.7 GB memory). Higher precision quants like Q5_K_M or Q6_K exceed typical consumer GPU limits.

What GPU do you need for defog_sqlcoder-34b-alpha?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q4_K_M (20.2 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (27.7 GB file, about 29.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (35.9 GB file, about 38.0 GB in use).

Which defog_sqlcoder-34b-alpha quant should you choose?

Q4_K_M is the usual starting point for defog_sqlcoder-34b-alpha: it balances file size and quality well. Here it is a 20.2 GB file.

The Q8_0 file is 35.9 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 14.2 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
Parameters33.7B
Layers48
Trained context16,384 tokens
KV cache (fp16)192 KB per token

Source

Quantized byTheBloke
FamilySqlcoder
Licensecc-by-4.0
Downloads (HF)1,560
Last updated2023-11-18

Frequently asked questions about defog_sqlcoder-34b-alpha

How much VRAM does defog_sqlcoder-34b-alpha need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 20.2 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 defog_sqlcoder-34b-alpha on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of defog_sqlcoder-34b-alpha GGUF?

It depends on the quant: Q2_K is 14.2 GB, Q3_K_S is 14.6 GB, Q3_K_M is 16.3 GB, Q3_K_L is 17.8 GB, Q4_0 is 19.1 GB, Q4_K_S is 19.1 GB and 6 more.

What context length does defog_sqlcoder-34b-alpha 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 defog_sqlcoder-34b-alpha GGUF?

The files are on Hugging Face in the TheBloke/sqlcoder-34b-alpha-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 defog_sqlcoder-34b-alpha 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 SQLCoder-34B Alpha on an RTX 3090 with 24GB VRAM?

Yes, the Q4_0 or Q4_K_S quantized models fit within 24GB VRAM and provide a good balance of speed and accuracy.

Does the model support multi‑language queries?

The model is trained for coding tasks; language support beyond English is not specified.

What context length does the model support?

The model supports up to 16384 tokens in context.

Other GGUFs of sqlcoder-34b-alpha

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Sqlcoder models

All Sqlcoder →

Other medium models

All medium models →