LL

upstage_llama-30b-instruct-2048

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

upstage_llama-30b-instruct-2048 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).

Upstage Llama‑30B Instruct 2048 in GGUF format

Upstage Llama‑30B Instruct 2048 is a 32.5 billion‑parameter Llama model fine‑tuned on English instruction data. It supports a context length of 2048 tokens and is available in multiple GGUF quantisations for llama.cpp and compatible libraries.

Good at

  • Instruction following
  • English text generation
  • Moderate‑size context handling

Limits

  • Requires large VRAM for full precision
  • No vision or multimodal support
  • License is non‑commercial

Best for

  • Chatbot back‑ends
  • Content drafting
  • Code assistance

Who it’s for. Developers and researchers needing a large‑scale instruction model for local inference. The model is suitable for users with access to the non‑commercial license and sufficient GPU memory.

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_K or Q4_K_S (≈32 GB memory at 8k context). For 12 GB VRAM, Q5_K_S or Q5_K_M (≈36 GB). For 16 GB VRAM, Q6_K (≈40 GB). Larger VRAM allows higher‑quality quants such as Q8_0.

What GPU do you need for upstage_llama-30b-instruct-2048?

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 upstage_llama-30b-instruct-2048 quant should you choose?

Q4_K_M is the usual starting point for upstage_llama-30b-instruct-2048: 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)3,241
Last updated2023-09-27

Frequently asked questions about upstage_llama-30b-instruct-2048

How much VRAM does upstage_llama-30b-instruct-2048 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 upstage_llama-30b-instruct-2048 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 upstage_llama-30b-instruct-2048 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 upstage_llama-30b-instruct-2048 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 upstage_llama-30b-instruct-2048 GGUF?

The files are on Hugging Face in the TheBloke/upstage-llama-30b-instruct-2048-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 upstage_llama-30b-instruct-2048 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_K or Q4_K_S quantised files; they require about 32 GB of memory at 8k context, which exceeds 8 GB VRAM, so it is not feasible.

Does this model support vision tasks?

No, the model has no vision or multimodal capabilities.

What license applies to this model?

The model is under a non‑commercial bespoke license governed by the Meta license.

Other GGUFs of llama-30b-instruct-2048

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Llama models

All Llama →

Other medium models

All medium models →