PR

prometheus-7b-v2.0

PrometheusGGUF by prometheus-evalUpdated 2024-07-12
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant4.4 GB
Quick answer

prometheus-7b-v2.0 needs about 5.9 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Prometheus 7B v2.0 – a 7.24B parameter language model

Prometheus 7B v2.0 is a 7.24B parameter llama architecture model trained for fine‑grained evaluation and RLHF. It supports 32768 context tokens and is released under Apache‑2.0. The model is available in a single Q4_K_M quantized GGUF file.

Good at

  • Fine‑grained evaluation
  • Reward modeling
  • English language tasks

Limits

  • No vision support
  • Requires 5.9GB VRAM at 8k context
  • Single quant available

Best for

  • Evaluating LLM outputs
  • Training RLHF pipelines
  • Benchmarking language models

Who it’s for. Researchers and developers needing a lightweight, open‑source model for evaluation and reinforcement learning tasks. The model is suitable for those who can run it on GPUs with at least 6GB VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.4 GB 5.9 GB
Fits Get file →

The only available quant is Q4_K_M with a file size of 4.37GB. It requires approximately 5.9GB VRAM at 8k context. For 8GB VRAM setups, this quant is suitable. No other quants are provided.

What GPU do you need for prometheus-7b-v2.0?

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: the best quant that fits is Q4_K_M (4.4 GB file, about 5.9 GB in use).

Which prometheus-7b-v2.0 quant should you choose?

Q4_K_M is the usual starting point for prometheus-7b-v2.0: it balances file size and quality well. Here it is a 4.4 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byprometheus-eval
Licenseapache-2.0
Downloads (HF)994
Last updated2024-07-12

Frequently asked questions about prometheus-7b-v2.0

How much VRAM does prometheus-7b-v2.0 need?

About 5.9 GB at Q4_K_M with an 8K context window. That is the 4.4 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-v2.0 on an 8 GB GPU?

Yes, with Q4_K_M: the 4.4 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of prometheus-7b-v2.0 GGUF?

It depends on the quant: Q4_K_M is 4.4 GB.

What context length does prometheus-7b-v2.0 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download prometheus-7b-v2.0 GGUF?

The files are on Hugging Face in the prometheus-eval/prometheus-7b-v2.0-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-v2.0 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 v2.0 on 8 GB VRAM?

Yes, the Q4_K_M quant requires about 5.9GB VRAM at 8k context, which fits within an 8GB VRAM budget.

Does the model support vision tasks?

No, it is a language model only.

Similar models

Browse all →

More Prometheus models

All Prometheus →

Other small models

All small models →