MP

Mpt 7b Storywriter

MptGGUF by mradermacherUpdated 2024-09-09
Download on Hugging Face
Parameters6.65B
Context64K
Layers32
Architecturempt
Smallest quant1.5 GB
Quick answer

Mpt 7b Storywriter needs about 9.1 GB of memory at Q4_K_M (a 4.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 1.5 GB (IQ1_S) to 5.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.

Mpt 7b Storywriter – a 7B parameter text generation model

Mpt 7b Storywriter is a 7 billion parameter language model trained on 65 536 token context. It is released under the Apache‑2.0 license and available in multiple GGUF quantizations. The model is designed for text generation tasks such as story writing and creative writing.

Good at

  • Long‑form text generation
  • Creative storytelling
  • Narrative continuation

Limits

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

Best for

  • Writing short stories
  • Generating plot outlines
  • Creative brainstorming

Who it’s for. Developers and writers who need a lightweight, open‑source model for generating narrative content. The model can be run locally using llama.cpp with the provided GGUF files.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.5 GB 6.3 GB
Fits Get file →
IQ1_M1.6 GB 6.4 GB
Fits Get file →
IQ2_XXS1.8 GB 6.6 GB
Fits Get file →
IQ2_XS2.0 GB 6.8 GB
Fits Get file →
IQ2_S2.1 GB 6.9 GB
Fits Get file →
IQ2_M2.3 GB 7.1 GB
Fits Get file →
Q2_K2.6 GB 7.4 GB
Tight Get file →
IQ3_XXS2.6 GB 7.4 GB
Tight Get file →
IQ3_XS2.9 GB 7.7 GB
Tight Get file →
IQ3_S2.9 GB 7.7 GB
Tight Get file →
Q3_K_S2.9 GB 7.7 GB
Tight Get file →
IQ3_M3.3 GB 8.1 GB
Too big Get file →
Q3_K_M3.5 GB 8.3 GB
Too big Get file →
IQ4_XS3.6 GB 8.4 GB
Too big Get file →
Q4_03.8 GB 8.6 GB
Too big Get file →
Q4_03.8 GB 8.6 GB
Too big Get file →
Q4_03.8 GB 8.6 GB
Too big Get file →
Q4_03.8 GB 8.6 GB
Too big Get file →
Q4_K_S3.8 GB 8.6 GB
Too big Get file →
Q3_K_L3.8 GB 8.6 GB
Too big Get file →
Q4_K_M4.3 GB 9.1 GB
Too big Get file →
Q5_K_S4.6 GB 9.4 GB
Too big Get file →
Q5_K_M5.0 GB 9.8 GB
Too big Get file →
Q6_K5.5 GB 10.3 GB
Too big Get file →

For 8 GB VRAM use Q4_0 (3.8 GB file, ~8.6 GB memory). With 12 GB VRAM Q5_K_M (4.96 GB file, ~9.8 GB memory) is suitable. For 16 GB VRAM Q6_K (5.46 GB file, ~10.3 GB memory) offers higher quality.

What GPU do you need for Mpt 7b Storywriter?

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 IQ3_S (2.9 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.5 GB file, about 10.3 GB in use).

Which Mpt 7b Storywriter quant should you choose?

Q4_K_M is the usual starting point for Mpt 7b Storywriter: it balances file size and quality well. Here it is a 4.3 GB file.

If memory is tight, the smallest file is IQ1_S at 1.5 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

Architecturempt
Parameters6.65B
Layers32
Trained context65,536 tokens
KV cache (fp16)512 KB per token

Source

Quantized bymradermacher
FamilyMpt
Licenseapache-2.0
Downloads (HF)4,286
Last updated2024-09-09

Frequently asked questions about Mpt 7b Storywriter

How much VRAM does Mpt 7b Storywriter need?

About 9.1 GB at Q4_K_M with an 8K context window. That is the 4.3 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 Mpt 7b Storywriter on an 8 GB GPU?

Yes, with IQ3_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 Mpt 7b Storywriter GGUF?

It depends on the quant: IQ1_S is 1.5 GB, IQ1_M is 1.6 GB, IQ2_XXS is 1.8 GB, IQ2_XS is 2.0 GB, IQ2_S is 2.1 GB, IQ2_M is 2.3 GB and 18 more.

What context length does Mpt 7b Storywriter support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 4.3 GB at 8K and 17.2 GB at 32K.

Where can I download Mpt 7b Storywriter GGUF?

The files are on Hugging Face in the mradermacher/mpt-7b-storywriter-i1-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 Mpt 7b Storywriter 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 Mpt 7b Storywriter on 8 GB VRAM?

Yes, use the Q4_0 quant which requires about 8.6 GB of VRAM at 8 k context.

Is the model open source?

It is released under the Apache‑2.0 license, allowing free use and modification.

Does it support image input?

No, the model has no vision capabilities and only processes text.

Other GGUFs of mpt-7b-storywriter

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mpt models

All Mpt →

Other small models

All small models →