AU

AutoCoder

AutocoderGGUF by legraphistaUpdated 2024-05-28
Download on Hugging Face
Parameters33.3B
Context16K
Layers62
Architecturellama
Smallest quant7.2 GB
Quick answer

AutoCoder needs about 17.6 GB of memory at IQ3_M (a 15.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 25 quants, from 7.2 GB (IQ1_S) to 66.7 GB.

AutoCoder – 33.3B llama model for code generation

AutoCoder is a 33.3B llama architecture model trained on 16384 context tokens. It excels at generating and executing code, with automatic package installation. The model is released under apache-2.0 and available in multiple GGUF quantizations.

Good at

  • Code generation
  • Automatic package installation
  • Running code snippets

Limits

  • No vision support
  • Large VRAM requirement for higher quants
  • Requires llama.cpp for inference

Best for

  • Developers needing code generation
  • Automated coding pipelines
  • Testing code execution

Who it’s for. Developers and researchers who need a high‑accuracy code generation model. The model supports automatic execution of generated code and is suitable for integration into coding assistants.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.2 GB 9.7 GB
Too big Get file →
IQ1_M7.8 GB 10.4 GB
Too big Get file →
IQ2_XXS8.9 GB 11.5 GB
Too big Get file →
IQ2_XS9.9 GB 12.5 GB
Too big Get file →
IQ2_S10.5 GB 13.1 GB
Too big Get file →
IQ2_M11.4 GB 13.9 GB
Too big Get file →
Q2_K_S11.4 GB 14.0 GB
Too big Get file →
Q2_K12.4 GB 14.9 GB
Too big Get file →
IQ3_XXS12.9 GB 15.4 GB
Too big Get file →
IQ3_XS13.7 GB 16.3 GB
Too big Get file →
Q3_K_S14.4 GB 17.0 GB
Too big Get file →
IQ3_S14.5 GB 17.1 GB
Too big Get file →
IQ3_M15.0 GB 17.6 GB
Too big Get file →
Q3_K16.1 GB 18.7 GB
Too big Get file →
Q3_K_L17.6 GB 20.1 GB
Too big Get file →
IQ4_XS17.9 GB 20.4 GB
Too big Get file →
IQ4_NL18.9 GB 21.5 GB
Too big Get file →
Q4_K_S18.9 GB 21.5 GB
Too big Get file →
Q4_K19.9 GB 22.5 GB
Too big Get file →
Q5_K_S23.0 GB 25.5 GB
Too big Get file →
Q5_K23.5 GB 26.1 GB
Too big Get file →
Q6_K27.4 GB 29.9 GB
Too big Get file →
Q8_035.4 GB 38.0 GB
Too big Get file →
BF1666.7 GB (3 parts) 69.3 GB
Too big Get file →
—66.7 GB (3 parts) 69.3 GB
Too big Get file →

For 8GB VRAM, use IQ1_S (est. 9.7GB) or IQ1_M (10.4GB). For 12GB VRAM, IQ2_S (13.1GB) or Q2_K_S (14GB). For 16GB VRAM, IQ3_S (17.1GB) or Q3_K (18.7GB). Higher quants need more VRAM and are not recommended for limited memory.

What GPU do you need for AutoCoder?

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 IQ2_XXS (8.9 GB file, about 11.5 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XXS (12.9 GB file, about 15.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K (19.9 GB file, about 22.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (27.4 GB file, about 29.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (35.4 GB file, about 38.0 GB in use).

Which AutoCoder quant should you choose?

IQ3_M (15.0 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 7.2 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
Parameters33.3B
Layers62
Trained context16,384 tokens
KV cache (fp16)248 KB per token

Source

Quantized bylegraphista
FamilyAutocoder
Licenseapache-2.0
Downloads (HF)1,397
Last updated2024-05-28

Frequently asked questions about AutoCoder

How much VRAM does AutoCoder need?

About 17.6 GB at IQ3_M with an 8K context window. That is the 15.0 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 AutoCoder on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of AutoCoder GGUF?

It depends on the quant: IQ1_S is 7.2 GB, IQ1_M is 7.8 GB, IQ2_XXS is 8.9 GB, IQ2_XS is 9.9 GB, IQ2_S is 10.5 GB, IQ2_M is 11.4 GB and 19 more.

What context length does AutoCoder support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 2.1 GB at 8K and 4.2 GB at 16K.

Where can I download AutoCoder GGUF?

The files are on Hugging Face in the legraphista/AutoCoder-IMat-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 AutoCoder 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 IQ1_S on 8GB VRAM?

IQ1_S requires approximately 9.7GB at 8k context, so it exceeds 8GB VRAM. Use a lower quant or reduce context size.

Does AutoCoder support vision tasks?

No, the model has no vision capabilities.

What license applies to AutoCoder?

The model is released under the apache-2.0 license.

Other GGUFs of AutoCoder

Similar models

Browse all →

More from legraphista

All by legraphista →

More Autocoder models

All Autocoder →

Other medium models

All medium models →