WI

WinterGoddess 1.4x limarpv3 70B L2 32k Requant

WintergoddessGGUF by NexesQuantsUpdated 2024-02-13
Download on Hugging Face
Parameters69B
Context32K
Layers80
Architecturellama
Smallest quant14.5 GB
Quick answer

WinterGoddess 1.4x limarpv3 70B L2 32k Requant needs about 28.6 GB of memory at Q2_K (a 25.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 12 quants, from 14.5 GB (IQ1_S) to 33.3 GB (Q3_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

70B Llama model with 32k context, requantized for varied VRAM

WinterGoddess 1.4x limarpv3 70B L2 32k Requant is a 69 billion‑parameter Llama model. It supports a 32 k token context and is available in multiple GGUF quantizations. The model is licensed under llama2.

Good at

  • Long‑form text generation
  • Context‑heavy dialogue
  • Fine‑tuned Llama architecture

Limits

  • No vision support
  • Requires large VRAM for full context
  • License restricts commercial use

Best for

  • Research prototypes
  • Large‑context chatbots
  • Custom fine‑tuning

Who it’s for. Developers and researchers needing a high‑capacity Llama model with extended context. The model is suitable for those who can manage the VRAM requirements and comply with the llama2 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S14.5 GB 17.7 GB
Too big Get file →
IQ2_XS20.3 GB 23.5 GB
Too big Get file →
Q2_K_S23.6 GB 26.7 GB
Too big Get file →
Q2_K_S23.6 GB 26.7 GB
Too big Get file →
Q2_K25.5 GB 28.6 GB
Too big Get file →
Q2_K25.5 GB 28.6 GB
Too big Get file →
Q2_K25.5 GB 28.6 GB
Too big Get file →
IQ3_XXS27.0 GB 30.2 GB
Too big Get file →
Q3_K_XS28.3 GB 31.4 GB
Too big Get file →
Q3_K_S29.9 GB 33.1 GB
Too big Get file →
Q3_K_S29.9 GB 33.1 GB
Too big Get file →
Q3_K_M33.3 GB 36.5 GB
Too big Get file →

For 8 GB VRAM use IQ1_S (file size 14.54 GB, memory 17.7 GB at 8k context). For 16 GB VRAM IQ2_XS (20.34 GB, 23.5 GB). For 24 GB VRAM Q2_K (25.46 GB, 28.6 GB). For 36 GB VRAM Q3_K_M (33.28 GB, 36.5 GB).

What GPU do you need for WinterGoddess 1.4x limarpv3 70B L2 32k Requant?

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: the best quant that fits is IQ2_XS (20.3 GB file, about 23.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q3_K_XS (28.3 GB file, about 31.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q3_K_M (33.3 GB file, about 36.5 GB in use).

Which WinterGoddess 1.4x limarpv3 70B L2 32k Requant quant should you choose?

Q2_K (25.5 GB) is the middle option in this repository. 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.

If memory is tight, the smallest file is IQ1_S at 14.5 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 context32,768 tokens
KV cache (fp16)320 KB per token

Source

Quantized byNexesQuants
Licensellama2
Downloads (HF)1,397
Last updated2024-02-13

Frequently asked questions about WinterGoddess 1.4x limarpv3 70B L2 32k Requant

How much VRAM does WinterGoddess 1.4x limarpv3 70B L2 32k Requant need?

About 28.6 GB at Q2_K with an 8K context window. That is the 25.5 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 WinterGoddess 1.4x limarpv3 70B L2 32k Requant on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of WinterGoddess 1.4x limarpv3 70B L2 32k Requant GGUF?

It depends on the quant: IQ1_S is 14.5 GB, IQ2_XS is 20.3 GB, Q2_K_S is 23.6 GB, Q2_K_S is 23.6 GB, Q2_K is 25.5 GB, Q2_K is 25.5 GB and 6 more.

What context length does WinterGoddess 1.4x limarpv3 70B L2 32k Requant support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download WinterGoddess 1.4x limarpv3 70B L2 32k Requant GGUF?

The files are on Hugging Face in the NexesQuants/WinterGoddess-1.4x-limarpv3-70B-L2-32k-Requant.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 WinterGoddess 1.4x limarpv3 70B L2 32k Requant 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?

Use the IQ1_S quant; it requires about 17.7 GB memory at 8k context, so it will need offloading or a smaller context.

Does the model support vision tasks?

No, the model has no vision capabilities.

What context length does it support?

The model is trained for 32 k tokens and supports up to that context length with the provided quantizations.

Similar models

Browse all →

More from NexesQuants

All by NexesQuants →

More Wintergoddess models

All Wintergoddess →

Other large models

All large models →