FI

Fimbulvetr-11B-v2

FimbulvetrGGUF by LewdiculousUpdated 2024-10-02
Download on Hugging Face
Parameters10.7B
Context4K
Layers48
Architecturellama
Smallest quant4.2 GB
Quick answer

Fimbulvetr-11B-v2 needs about 8.6 GB of memory at Q4_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 10 quants, from 4.2 GB (IQ3_XXS) to 11.4 GB (Q8_0).

Fimbulvetr‑11B‑v2, a 10.7B llama model focused on roleplay

Fimbulvetr‑11B‑v2 is a 10.7B parameter llama model trained on 4096 context tokens. It is available in multiple GGUF quantizations and supports Alpaca or Vicuna prompt formats. The model is licensed under cc‑by‑nc‑4.0.

Good at

  • Roleplay scenarios
  • Alpaca/Vicuna prompt compatibility
  • Compact quant options

Limits

  • No vision support
  • CC‑BY‑NC license restricts commercial use
  • Requires 8k context for memory estimates

Best for

  • Chatbot roleplay scripts
  • Interactive storytelling
  • Non‑commercial content creation

Who it’s for. Developers building roleplay‑centric chatbots or interactive fiction tools. Researchers needing a non‑commercial llama model with flexible quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS4.2 GB 5.5 GB
Fits Get file →
IQ3_S4.7 GB 6.0 GB
Fits Get file →
IQ3_M4.8 GB 6.2 GB
Fits Get file →
IQ4_XS5.8 GB 7.1 GB
Fits Get file →
Q4_K_S6.1 GB 7.4 GB
Tight Get file →
Q4_K_M6.5 GB 7.8 GB
Tight Get file →
Q5_K_S7.4 GB 8.7 GB
Too big Get file →
Q5_K_M7.6 GB 8.9 GB
Too big Get file →
Q6_K8.8 GB 10.1 GB
Too big Get file →
Q8_011.4 GB 12.7 GB
Too big Get file →

For 8 GB VRAM, use IQ3_XXS (file size 4.17 GB, memory 6.3 GB) or IQ3_S (4.69 GB, 6.8 GB). If 12 GB VRAM is available, Q4_K_M (6.46 GB, 8.6 GB) or Q5_K_M (7.6 GB, 9.7 GB) provide better quality. Larger models like Q8_0 need 13.5 GB memory and 11.4 GB file size.

What GPU do you need for Fimbulvetr-11B-v2?

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 IQ4_XS (5.8 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.8 GB file, about 10.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.4 GB file, about 13.5 GB in use).

Which Fimbulvetr-11B-v2 quant should you choose?

Q4_K_M is the usual starting point for Fimbulvetr-11B-v2: it balances file size and quality well. Here it is a 6.5 GB file.

The Q8_0 file is 11.4 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 IQ3_XXS at 4.2 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters10.7B
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized byLewdiculous
Downloads (HF)502
Last updated2024-10-02

Frequently asked questions about Fimbulvetr-11B-v2

How much VRAM does Fimbulvetr-11B-v2 need?

About 8.6 GB at Q4_K_M with an 8K context window. That is the 6.5 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 Fimbulvetr-11B-v2 on an 8 GB GPU?

Yes, with IQ4_XS: the 5.8 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Fimbulvetr-11B-v2 GGUF?

It depends on the quant: IQ3_XXS is 4.2 GB, IQ3_S is 4.7 GB, IQ3_M is 4.8 GB, IQ4_XS is 5.8 GB, Q4_K_S is 6.1 GB, Q4_K_M is 6.5 GB and 4 more.

What context length does Fimbulvetr-11B-v2 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download Fimbulvetr-11B-v2 GGUF?

The files are on Hugging Face in the Lewdiculous/Fimbulvetr-11B-v2-GGUF-IQ-Imatrix repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Fimbulvetr-11B-v2 use?

Hugging Face lists the license as cc-by-nc-4.0. 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 Fimbulvetr‑11B‑v2 on 8 GB VRAM?

Yes, use IQ3_XXS or IQ3_S quantizations; they require about 6.3–6.8 GB memory at 8k context.

Does the model support image inputs?

No, the model has no vision capabilities.

Is the model free for commercial use?

No, it is licensed under cc‑by‑nc‑4.0, so commercial use is not permitted.

Other GGUFs of Fimbulvetr-11B-v2

Similar models

Browse all →

More from Lewdiculous

All by Lewdiculous →

More Fimbulvetr models

All Fimbulvetr →

Other medium models

All medium models →