LL

ausboss_llama-30b-supercot

LlamaGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters32.5B
Context2K
Layers60
Architecturellama
Smallest quant13.5 GB
Quick answer

ausboss_llama-30b-supercot needs about 33.2 GB of memory at Q4_K_M (a 19.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 13.5 GB (Q2_K) to 34.6 GB (Q8_0).

32.5B‑parameter Llama 30B Supercot in GGUF format

ausboss_llama-30b-supercot is a 32.5B‑parameter Llama model fine‑tuned with SuperCOT LoRA. It supports 2048‑token context and is available in multiple GGUF quantisations. The model is designed for local inference via llama.cpp and compatible clients.

Good at

  • Fine‑tuned for LangChain prompting
  • Supports 2048‑token context
  • Compatible with 4‑bit quantised LLaMa models

Limits

  • No vision support
  • License is other, not standard
  • Requires large VRAM for higher quants

Best for

  • Local chat applications
  • LangChain‑based workflows
  • Fine‑tuned prompt engineering

Who it’s for. Developers and researchers who need a large Llama model with SuperCOT fine‑tuning for local inference. The model is suitable for those using llama.cpp or compatible GUIs and who can manage the memory requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K13.5 GB 17.3 GB
Too big Get file →
Q3_K_S14.1 GB 17.8 GB
Too big Get file →
Q3_K_M15.8 GB 19.5 GB
Too big Get file →
Q3_K_L17.3 GB 21.1 GB
Too big Get file →
Q4_018.4 GB 22.1 GB
Too big Get file →
Q4_K_S18.4 GB 22.2 GB
Too big Get file →
Q4_K_M19.6 GB 23.4 GB
Too big Get file →
Q5_022.4 GB 26.2 GB
Too big Get file →
Q5_K_S22.4 GB 26.2 GB
Too big Get file →
Q5_K_M23.0 GB 26.8 GB
Too big Get file →
Q6_K26.7 GB 30.5 GB
Too big Get file →
Q8_034.6 GB 38.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 18.36 GB, memory 31.9 GB). For 16 GB VRAM, Q5_0 (22.4 GB, 36 GB) or Q5_K_M (23.05 GB, 36.6 GB). For 24 GB VRAM, Q6_K (26.69 GB, 40.3 GB) or Q8_0 (34.57 GB, 48.2 GB). Estimates are approximate.

What GPU do you need for ausboss_llama-30b-supercot?

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q4_K_S (18.4 GB file, about 32.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (26.7 GB file, about 40.3 GB in use).

Which ausboss_llama-30b-supercot quant should you choose?

Q4_K_M is the usual starting point for ausboss_llama-30b-supercot: it balances file size and quality well. Here it is a 19.6 GB file.

The Q8_0 file is 34.6 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 13.5 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
Parameters32.5B
Layers60
Trained context2,048 tokens
KV cache (fp16)1560 KB per token

Source

Quantized byTheBloke
FamilyLlama
Licenseother
Downloads (HF)2,417
Last updated2023-09-27

Frequently asked questions about ausboss_llama-30b-supercot

How much VRAM does ausboss_llama-30b-supercot need?

About 33.2 GB at Q4_K_M with an 8K context window. That is the 19.6 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 ausboss_llama-30b-supercot on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 27.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ausboss_llama-30b-supercot GGUF?

It depends on the quant: Q2_K is 13.5 GB, Q3_K_S is 14.1 GB, Q3_K_M is 15.8 GB, Q3_K_L is 17.3 GB, Q4_0 is 18.4 GB, Q4_K_S is 18.4 GB and 6 more.

What context length does ausboss_llama-30b-supercot support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 13.1 GB at 8K and 3.3 GB at 2K.

Where can I download ausboss_llama-30b-supercot GGUF?

The files are on Hugging Face in the TheBloke/llama-30b-supercot-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 ausboss_llama-30b-supercot use?

Hugging Face lists the license as other. 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?

Use the Q4_0 quantisation; it requires about 31.9 GB of VRAM at 8k context, so 8 GB is insufficient.

Does this model support vision tasks?

No, the model has no vision capabilities.

Which clients support GGUF for this model?

Clients such as llama.cpp, text-generation-webui, KoboldCpp, LM Studio, LoLLMS Web UI, Faraday.dev, ctransformers, llama-cpp-python, and candle support GGUF.

Other GGUFs of llama-30b-supercot

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other medium models

All medium models →