PR

prometheus 7B v1.0

PrometheusGGUF by TheBlokeUpdated 2023-11-10
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant2.8 GB
Quick answer

prometheus 7B v1.0 needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 2.8 GB (Q2_K) to 7.2 GB (Q8_0).

Prometheus 7B v1.0 – a fine‑tuned Llama‑2‑Chat model for evaluation and RLHF

Prometheus 7B v1.0 is a 6.74B‑parameter language model based on Llama‑2‑Chat. It is fine‑tuned on 100K feedback samples for evaluating long‑form responses and can serve as a reward model for RLHF. The model is released under Apache‑2.0.

Good at

  • Evaluating long‑form responses
  • Reward modeling for RLHF
  • Customizable scoring rubrics

Limits

  • Requires 8‑k context for memory estimates
  • No vision support
  • License is Apache‑2.0

Best for

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

Who it’s for. Developers building evaluation tools for large language models and researchers needing a cost‑effective alternative to GPT‑4 for fine‑grained assessment. The model is suitable for those who can provide the required prompt format and are comfortable with GGUF deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.8 GB 5.5 GB
Fits Get file →
Q3_K_S2.9 GB 5.6 GB
Fits Get file →
Q3_K_M3.3 GB 5.9 GB
Fits Get file →
Q3_K_L3.6 GB 6.2 GB
Fits Get file →
Q4_03.8 GB 6.5 GB
Fits Get file →
Q4_K_S3.9 GB 6.5 GB
Fits Get file →
Q4_K_M4.1 GB 6.7 GB
Fits Get file →
Q5_04.7 GB 7.3 GB
Tight Get file →
Q5_K_S4.7 GB 7.3 GB
Tight Get file →
Q5_K_M4.8 GB 7.4 GB
Tight Get file →
Q6_K5.5 GB 8.2 GB
Too big Get file →
Q8_07.2 GB 9.8 GB
Too big Get file →

For 8‑GB VRAM, use Q4_0 (est. 8.6 GB) or Q4_K_S (est. 8.7 GB). If 12‑GB VRAM is available, Q8_0 (est. 12 GB) gives the highest quality. Lower‑bit options such as Q2_K (est. 7.6 GB) can run on 8‑GB VRAM but with reduced precision.

What GPU do you need for prometheus 7B 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: the best quant that fits is Q3_K_S (2.9 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).

Which prometheus 7B v1.0 quant should you choose?

Q4_K_M is the usual starting point for prometheus 7B v1.0: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.2 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 2.8 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
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byTheBloke
Licenseapache-2.0
Downloads (HF)2,060
Last updated2023-11-10

Frequently asked questions about prometheus 7B v1.0

How much VRAM does prometheus 7B v1.0 need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 7B v1.0 on an 8 GB GPU?

Yes, with Q3_K_S: the 2.9 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of prometheus 7B v1.0 GGUF?

It depends on the quant: Q2_K is 2.8 GB, Q3_K_S is 2.9 GB, Q3_K_M is 3.3 GB, Q3_K_L is 3.6 GB, Q4_0 is 3.8 GB, Q4_K_S is 3.9 GB and 6 more.

What context length does prometheus 7B 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 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download prometheus 7B v1.0 GGUF?

The files are on Hugging Face in the TheBloke/prometheus-7B-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 7B 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 7B v1.0 on 8 GB VRAM?

Yes, using Q4_0 or Q4_K_S quantisations will fit within 8 GB VRAM, though Q2_K may be more memory efficient but with lower precision.

What context length does Prometheus support?

The model was trained with 4096 tokens and the memory estimates are based on an 8‑k context size.

Is Prometheus available for commercial use?

The model is licensed under Apache‑2.0, which allows commercial use with attribution.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Prometheus models

All Prometheus →

Other small models

All small models →