MI

Ministrations 8B v1

MinistrationsGGUF by TheDrummerUpdated 2024-11-08
Download on Hugging Face
Parameters8.02B
Context32K
Layers36
Architecturellama
Smallest quant3.2 GB
Quick answer

Ministrations 8B v1 needs about 6.6 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 8 quants, from 3.2 GB (Q2_K) to 16.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Ministrations 8B v1 – a 8.02B‑parameter llama finetune for role‑playing

Ministrations 8B v1 is a 8.02B‑parameter llama model fine‑tuned for role‑playing. It supports tools and offers several quantized GGUF variants. The model was trained with a context of 32768 tokens.

Good at

  • Role‑playing dialogue
  • Tool usage
  • First‑person narration

Limits

  • No vision support
  • License type is other
  • Requires 8.53 GB for Q8_0 quant

Best for

  • Chatbot scripts
  • Interactive fiction
  • Narrative generation

Who it’s for. Developers building role‑playing chatbots or interactive fiction engines. The model is suitable for users who need a large context window and tool integration.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.2 GB 4.9 GB
Fits Get file →
Q3_K_M4.0 GB 5.7 GB
Fits Get file →
Q4_K_M4.9 GB 6.6 GB
Fits Get file →
Q5_K_M5.7 GB 7.4 GB
Tight Get file →
Q6_K6.6 GB 8.3 GB
Too big Get file →
Q8_08.5 GB 10.2 GB
Too big Get file →
BF1616.0 GB 17.8 GB
Too big Get file →
F1616.0 GB 17.8 GB
Too big Get file →

For 8 GB VRAM use Q2_K (3.19 GB, ~4.9 GB RAM). For 12 GB VRAM use Q4_K_M (4.91 GB, ~6.6 GB RAM). For 16 GB VRAM use Q6_K (6.59 GB, ~8.3 GB RAM).

What GPU do you need for Ministrations 8B v1?

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 Q3_K_M (4.0 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.2 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (16.0 GB file, about 17.8 GB in use).

Which Ministrations 8B v1 quant should you choose?

Q4_K_M is the usual starting point for Ministrations 8B v1: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.5 GB, about 1.7 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 3.2 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
Parameters8.02B
Layers36
Trained context32,768 tokens
KV cache (fp16)144 KB per token

Source

Quantized byTheDrummer
Licenseother
Downloads (HF)949
Last updated2024-11-08

Frequently asked questions about Ministrations 8B v1

How much VRAM does Ministrations 8B v1 need?

About 6.6 GB at Q4_K_M with an 8K context window. That is the 4.9 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 Ministrations 8B v1 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ministrations 8B v1 GGUF?

It depends on the quant: Q2_K is 3.2 GB, Q3_K_M is 4.0 GB, Q4_K_M is 4.9 GB, Q5_K_M is 5.7 GB, Q6_K is 6.6 GB, Q8_0 is 8.5 GB and 2 more.

What context length does Ministrations 8B v1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Ministrations 8B v1 GGUF?

The files are on Hugging Face in the TheDrummer/Ministrations-8B-v1-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 Ministrations 8B v1 use?

Hugging Face lists the license as other. 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 Q4_K_M on 8 GB VRAM?

No, Q4_K_M requires about 6.6 GB RAM at 8k context, which exceeds 8 GB VRAM when accounting for overhead.

Does this model support vision?

No, the model has no vision capabilities.

What chat templates are supported?

Metharme, Mistral Tekken, and custom templates can be used.

Similar models

Browse all →

More from TheDrummer

All by TheDrummer →

More Ministrations models

All Ministrations →

Other small models

All small models →