ST

Story Reverse Prompt 70b Rope8 32K Fp16

StoryGGUF by mradermacherUpdated 2024-08-30
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant25.5 GB
Quick answer

Story Reverse Prompt 70b Rope8 32K Fp16 needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 25.5 GB (Q2_K) to 48.8 GB (Q5_K_M).

Story Reverse Prompt 70b Rope8 32K Fp16 – converts story chunks into prompt format

This 69‑billion‑parameter llama model generates prompts from story text. It supports up to 32K context tokens and is designed for third‑person narratives. The model is available in multiple GGUF quantizations.

Good at

  • Generating Q&A prompts from story chunks
  • Maintaining context across long stories
  • Producing natural‑sounding prompts

Limits

  • Requires large VRAM (≈28.6 GB for Q2_K at 8K context)
  • Not user‑friendly for first‑person stories
  • No vision support

Best for

  • Training instruct‑tuned story writers
  • Automating prompt creation for long narratives
  • Batch processing of ePUB stories

Who it’s for. Developers and researchers who need to convert narrative text into structured prompts for training or generation tasks. The model is best suited for third‑person stories and works best when stories are split into chunks of fewer than 3000 tokens.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K25.5 GB 27.3 GB
Too big Get file →
IQ3_XS28.3 GB 30.2 GB
Too big Get file →
IQ3_S29.9 GB 31.8 GB
Too big Get file →
Q3_K_S29.9 GB 31.8 GB
Too big Get file →
IQ3_M30.9 GB 32.8 GB
Too big Get file →
Q3_K_M33.3 GB 35.1 GB
Too big Get file →
Q3_K_L36.1 GB 38.0 GB
Too big Get file →
IQ4_XS37.2 GB 39.0 GB
Too big Get file →
Q4_K_S39.2 GB 41.1 GB
Too big Get file →
Q4_K_M41.4 GB 43.3 GB
Too big Get file →
Q5_K_S47.5 GB 49.3 GB
Too big Get file →
Q5_K_M48.8 GB 50.6 GB
Too big Get file →

For 32 GB VRAM, Q2_K (25.46 GB file, 28.6 GB memory) is a good fit. If you have 40 GB VRAM, Q4_K_S (39.25 GB file, 42.4 GB memory) works well. For 50 GB VRAM, Q5_K_S (47.46 GB file, 50.6 GB memory) is recommended. Memory estimates are approximate.

What GPU do you need for Story Reverse Prompt 70b Rope8 32K Fp16?

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 IQ3_XS (28.3 GB file, about 31.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which Story Reverse Prompt 70b Rope8 32K Fp16 quant should you choose?

Q4_K_M is the usual starting point for Story Reverse Prompt 70b Rope8 32K Fp16: it balances file size and quality well. Here it is a 41.4 GB file.

If memory is tight, the smallest file is Q2_K at 25.5 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
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyStory
Licensellama2
Downloads (HF)1,614
Last updated2024-08-30

Frequently asked questions about Story Reverse Prompt 70b Rope8 32K Fp16

How much VRAM does Story Reverse Prompt 70b Rope8 32K Fp16 need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 Story Reverse Prompt 70b Rope8 32K Fp16 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Story Reverse Prompt 70b Rope8 32K Fp16 GGUF?

It depends on the quant: Q2_K is 25.5 GB, IQ3_XS is 28.3 GB, IQ3_S is 29.9 GB, Q3_K_S is 29.9 GB, IQ3_M is 30.9 GB, Q3_K_M is 33.3 GB and 6 more.

What context length does Story Reverse Prompt 70b Rope8 32K Fp16 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download Story Reverse Prompt 70b Rope8 32K Fp16 GGUF?

The files are on Hugging Face in the mradermacher/story-reverse-prompt-70b-rope8-32K-fp16-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 Story Reverse Prompt 70b Rope8 32K Fp16 use?

Hugging Face lists the license as llama2. 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?

No. Even the smallest quant requires at least 28.6 GB of VRAM at 8K context.

Is 16 GB VRAM sufficient?

No. The minimum memory requirement is above 28 GB for the smallest quant.

Can I run it on 32 GB VRAM?

Yes. Q2_K or Q4_K_S quantizations fit within a 32 GB VRAM budget.

Other GGUFs of story-reverse-prompt-70b-rope8-32K-fp16

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Story models

All Story →

Other large models

All large models →