WO

MN WORDSTORM pt4 RCM Cliffhanger 18.5B Instruct

WordstormGGUF by DavidAUUpdated 2024-11-14
Download on Hugging Face
Parameters18.5B
Context1000K
Layers63
Architecturellama
Smallest quant7.1 GB
Quick answer

MN WORDSTORM pt4 RCM Cliffhanger 18.5B Instruct needs about 13.8 GB of memory at Q4_K_M (a 11.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 11 quants, from 7.1 GB (Q2_K) to 19.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.5 GB.

18.5B instruction model for detailed story and roleplay

MN WORDSTORM pt4 RCM Cliffhanger 18.5B Instruct is a 18.5B parameter model built on Mistral Nemo architecture. It merges three high‑scoring Mistral Nemo variants with Instruct fine‑tuning. The model supports up to 1,024,000 context tokens and is licensed under Apache‑2.0.

Good at

  • Detailed creative writing
  • Roleplay with internal thoughts
  • Emotionally rich prose

Limits

  • No vision support
  • Large VRAM requirement for higher quants
  • Requires 8K context for memory estimates

Best for

  • Writing long narratives
  • Interactive roleplay sessions
  • Generating character backstories

Who it’s for. Developers and writers who need a large, instruction‑following model for creative content. The model is suitable for local deployment with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K7.1 GB 9.7 GB
Too big Get file →
Q3_K_S8.2 GB 10.8 GB
Too big Get file →
Q3_K_M9.1 GB 11.7 GB
Too big Get file →
Q3_K_L9.8 GB 12.5 GB
Too big Get file →
IQ4_XS10.2 GB 12.8 GB
Too big Get file →
Q4_K_S10.7 GB 13.3 GB
Too big Get file →
Q4_K_M11.2 GB 13.8 GB
Too big Get file →
Q5_K_S12.8 GB 15.4 GB
Too big Get file →
Q5_K_M13.2 GB 15.8 GB
Too big Get file →
Q6_K15.2 GB 17.8 GB
Too big Get file →
Q8_019.7 GB 22.3 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (7.1 GB file, ~9.7 GB memory at 8 k context). For 12 GB VRAM, Q4_K_S (10.67 GB file, ~13.3 GB memory) is a good balance. For 24 GB VRAM, Q6_K (15.2 GB file, ~17.8 GB memory) offers higher quality.

What GPU do you need for MN WORDSTORM pt4 RCM Cliffhanger 18.5B Instruct?

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: the best quant that fits is Q3_K_M (9.1 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (13.2 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (19.7 GB file, about 22.3 GB in use).

Which MN WORDSTORM pt4 RCM Cliffhanger 18.5B Instruct quant should you choose?

Q4_K_M is the usual starting point for MN WORDSTORM pt4 RCM Cliffhanger 18.5B Instruct: it balances file size and quality well. Here it is a 11.2 GB file.

The Q8_0 file is 19.7 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 7.1 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
Parameters18.5B
Layers63
Trained context1,024,000 tokens
KV cache (fp16)252 KB per token

Source

Quantized byDavidAU
FamilyWordstorm
Licenseapache-2.0
Downloads (HF)978
Last updated2024-11-14

Frequently asked questions about MN WORDSTORM pt4 RCM Cliffhanger 18.5B Instruct

How much VRAM does MN WORDSTORM pt4 RCM Cliffhanger 18.5B Instruct need?

About 13.8 GB at Q4_K_M with an 8K context window. That is the 11.2 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 MN WORDSTORM pt4 RCM Cliffhanger 18.5B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MN WORDSTORM pt4 RCM Cliffhanger 18.5B Instruct GGUF?

It depends on the quant: Q2_K is 7.1 GB, Q3_K_S is 8.2 GB, Q3_K_M is 9.1 GB, Q3_K_L is 9.8 GB, IQ4_XS is 10.2 GB, Q4_K_S is 10.7 GB and 5 more.

What context length does MN WORDSTORM pt4 RCM Cliffhanger 18.5B Instruct support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.5 GB at 32K.

Where can I download MN WORDSTORM pt4 RCM Cliffhanger 18.5B Instruct GGUF?

The files are on Hugging Face in the DavidAU/MN-WORDSTORM-pt4-RCM-Cliffhanger-18.5B-Instruct-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 MN WORDSTORM pt4 RCM Cliffhanger 18.5B Instruct 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 this model on 8 GB VRAM?

Yes, using the Q2_K quantization which requires about 9.7 GB of VRAM at 8 k context.

Does the model support vision?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from DavidAU

All by DavidAU →

More Wordstorm models

All Wordstorm →

Other medium models

All medium models →