PR

prometheus 13B v1.0

PrometheusGGUF by TheBlokeUpdated 2023-11-10
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

prometheus 13B v1.0 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).

Prometheus 13B v1.0 – a fine‑tuned Llama‑2‑Chat model for evaluation and RLHF

Prometheus 13B v1.0 is a 13‑billion‑parameter language model based on Llama‑2‑Chat. It is fine‑tuned on 100 K feedback samples for evaluating long‑form responses and can serve as a reward model for RLHF. The model is released under Apache 2.0 and is available in GGUF format.

Good at

  • Fine‑tuned evaluation of long‑form responses
  • Reward modeling for RLHF
  • Customizable scoring with reference answers

Limits

  • Requires 4096‑token context
  • No vision or multimodal support
  • Large memory footprint for higher quants

Best for

  • LLM evaluation pipelines
  • RLHF reward modeling
  • Custom benchmark creation

Who it’s for. Developers and researchers building evaluation tools for large language models. The model is suitable for teams needing a cost‑effective alternative to GPT‑4 for scoring and feedback generation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.4 GB 9.3 GB
Too big Get file →
Q3_K_S5.7 GB 9.5 GB
Too big Get file →
Q3_K_M6.3 GB 10.2 GB
Too big Get file →
Q3_K_L6.9 GB 10.8 GB
Too big Get file →
Q4_07.4 GB 11.2 GB
Too big Get file →
Q4_K_S7.4 GB 11.3 GB
Too big Get file →
Q4_K_M7.9 GB 11.7 GB
Too big Get file →
Q5_09.0 GB 12.8 GB
Too big Get file →
Q5_K_S9.0 GB 12.8 GB
Too big Get file →
Q5_K_M9.2 GB 13.1 GB
Too big Get file →
Q6_K10.7 GB 14.5 GB
Too big Get file →
Q8_013.8 GB 17.7 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (est. 15.1 GB memory at 8 k context). With 12 GB VRAM Q5_K_M (16.4 GB) is possible on high‑end GPUs. For CPU‑only inference, Q2_K (12.6 GB) or Q3_K_S (12.9 GB) are recommended.

What GPU do you need for prometheus 13B v1.0?

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 prometheus 13B v1.0 quant should you choose?

Q4_K_M is the usual starting point for prometheus 13B v1.0: 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 context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byTheBloke
Licenseapache-2.0
Downloads (HF)2,631
Last updated2023-11-10

Frequently asked questions about prometheus 13B v1.0

How much VRAM does prometheus 13B v1.0 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 prometheus 13B v1.0 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 prometheus 13B v1.0 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 prometheus 13B v1.0 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download prometheus 13B v1.0 GGUF?

The files are on Hugging Face in the TheBloke/prometheus-13B-v1.0-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 prometheus 13B v1.0 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 Prometheus 13B v1.0 on 8 GB VRAM?

Yes, using the Q4_K_M quantization which requires approximately 15.1 GB of VRAM at 8 k context, but you may need to reduce batch size or use CPU fallback.

Does the model support vision or multimodal inputs?

No, Prometheus 13B v1.0 is a text‑only language model with no vision capabilities.

What license applies to the model?

The model is released under the Apache 2.0 license, allowing free use and modification.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Prometheus models

All Prometheus →

Other medium models

All medium models →