LL

openassistant_codellama-13b-oasst-sft-v10

LlamaGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters13B
Context16K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

openassistant_codellama-13b-oasst-sft-v10 needs about 15.1 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 12 quants, from 5.4 GB (Q2_K) to 13.8 GB (Q8_0).

Open-Assistant fine‑tuned CodeLlama 13B for coding tasks

This model is a 13‑billion parameter Llama family model fine‑tuned by Open‑Assistant for coding. It supports up to 16,384 context tokens and is released under the LLAMA 2 COMMUNITY LICENSE. The model is available in GGUF format for local inference.

Good at

  • Coding assistance
  • Code generation
  • Debugging suggestions

Limits

  • No vision support
  • Requires trust_remote_code=True or latest transformers
  • Large VRAM needed for higher quant levels

Best for

  • Developers needing local code generation
  • Educational coding tools
  • Automated code review scripts

Who it’s for. Developers and researchers who want a local, open‑source coding assistant. The model is suitable for integration into IDE plugins or custom web interfaces.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.4 GB 12.6 GB
Too big Get file →
Q3_K_S5.7 GB 12.9 GB
Too big Get file →
Q3_K_M6.3 GB 13.5 GB
Too big Get file →
Q3_K_L6.9 GB 14.1 GB
Too big Get file →
Q4_07.4 GB 14.6 GB
Too big Get file →
Q4_K_S7.4 GB 14.6 GB
Too big Get file →
Q4_K_M7.9 GB 15.1 GB
Too big Get file →
Q5_09.0 GB 16.2 GB
Too big Get file →
Q5_K_S9.0 GB 16.2 GB
Too big Get file →
Q5_K_M9.2 GB 16.4 GB
Too big Get file →
Q6_K10.7 GB 17.9 GB
Too big Get file →
Q8_013.8 GB 21.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (≈15 GB memory at 8 k context) or Q3_K_M (≈13.5 GB). For 12 GB VRAM, Q4_0 or Q4_K_S are suitable. Higher quant levels such as Q5_K_M or Q6_K require 16–18 GB VRAM.

What GPU do you need for openassistant_codellama-13b-oasst-sft-v10?

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: the best quant that fits is Q4_K_M (7.9 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).

Which openassistant_codellama-13b-oasst-sft-v10 quant should you choose?

Q4_K_M is the usual starting point for openassistant_codellama-13b-oasst-sft-v10: it balances file size and quality well. Here it is a 7.9 GB file.

The Q8_0 file is 13.8 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 5.4 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
Parameters13B
Layers40
Trained context16,384 tokens
KV cache (fp16)800 KB per token

Source

Quantized byTheBloke
FamilyLlama
Licensellama2
Downloads (HF)12,296
Last updated2023-09-27

Frequently asked questions about openassistant_codellama-13b-oasst-sft-v10

How much VRAM does openassistant_codellama-13b-oasst-sft-v10 need?

About 15.1 GB at Q4_K_M with an 8K context window. That is the 7.9 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 openassistant_codellama-13b-oasst-sft-v10 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of openassistant_codellama-13b-oasst-sft-v10 GGUF?

It depends on the quant: Q2_K is 5.4 GB, Q3_K_S is 5.7 GB, Q3_K_M is 6.3 GB, Q3_K_L is 6.9 GB, Q4_0 is 7.4 GB, Q4_K_S is 7.4 GB and 6 more.

What context length does openassistant_codellama-13b-oasst-sft-v10 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 6.7 GB at 8K and 13.4 GB at 16K.

Where can I download openassistant_codellama-13b-oasst-sft-v10 GGUF?

The files are on Hugging Face in the TheBloke/CodeLlama-13B-oasst-sft-v10-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 openassistant_codellama-13b-oasst-sft-v10 use?

Hugging Face lists the license as llama2. 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 this model on 8 GB VRAM?

Yes, with Q4_K_M or Q3_K_M quantisation, which use about 15 GB or 13.5 GB of VRAM at 8 k context.

Does the model support image inputs?

No, this model only handles text and does not support vision.

What license applies to this model?

The model is released under the LLAMA 2 COMMUNITY LICENSE AGREEMENT.

Other GGUFs of codellama-13b-oasst-sft-v10

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other medium models

All medium models →