BI

BigWeave v26 95b

BigweaveGGUF by mradermacherUpdated 2024-11-30
Download on Hugging Face
Parameters94.6B
Context32K
Layers110
Architecturellama
Smallest quant19.9 GB
Quick answer

BigWeave v26 95b needs about 39.0 GB of memory at Q2_K (a 34.8 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 14 quants, from 19.9 GB (IQ1_S) to 49.6 GB (Q3_K_L).

BigWeave v26 95b – 94.6B‑parameter LLaMA‑style model

BigWeave v26 95b is a 94.6B‑parameter LLaMA‑based model. It supports chatml, Mistral, and Vicuna prompting formats. The model is available in multiple quantizations for different memory budgets.

Good at

  • Chat‑style dialogue
  • Large context handling
  • High‑parameter reasoning

Limits

  • No vision support
  • License unknown
  • No mixture of experts

Best for

  • Chatbot development
  • Research prototyping
  • Large‑context inference

Who it’s for. Developers and researchers who need a large‑parameter LLaMA model with flexible prompting. The model is suitable for those who can manage the memory requirements of the various quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S19.9 GB 24.1 GB
Too big Get file →
IQ1_M21.8 GB 26.0 GB
Too big Get file →
IQ2_XXS25.0 GB 29.2 GB
Too big Get file →
IQ2_XS27.9 GB 32.0 GB
Too big Get file →
IQ2_S29.2 GB 33.4 GB
Too big Get file →
IQ2_M31.8 GB 36.0 GB
Too big Get file →
Q2_K34.8 GB 39.0 GB
Too big Get file →
IQ3_XXS36.3 GB 40.5 GB
Too big Get file →
IQ3_XS38.7 GB 42.9 GB
Too big Get file →
Q3_K_S40.8 GB 45.0 GB
Too big Get file →
IQ3_S40.9 GB 45.1 GB
Too big Get file →
IQ3_M42.3 GB 46.5 GB
Too big Get file →
Q3_K_M45.5 GB 49.7 GB
Too big Get file →
Q3_K_L49.6 GB 53.8 GB
Too big Get file →

For 8 GB VRAM use IQ1_S (file size 19.86 GB, estimated 24.1 GB memory). For 12 GB VRAM use IQ1_M (21.8 GB, 26 GB memory). For 16 GB VRAM use IQ2_XS (27.85 GB, 32 GB memory).

What GPU do you need for BigWeave v26 95b?

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is IQ2_XS (27.9 GB file, about 32.0 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ3_M (42.3 GB file, about 46.5 GB in use).

Which BigWeave v26 95b quant should you choose?

Q2_K (34.8 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 19.9 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
Parameters94.6B
Layers110
Trained context32,764 tokens
KV cache (fp16)440 KB per token

Source

Quantized bymradermacher
FamilyBigweave
Licenseunknown
Downloads (HF)799
Last updated2024-11-30

Frequently asked questions about BigWeave v26 95b

How much VRAM does BigWeave v26 95b need?

About 39.0 GB at Q2_K with an 8K context window. That is the 34.8 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 BigWeave v26 95b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 24.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of BigWeave v26 95b GGUF?

It depends on the quant: IQ1_S is 19.9 GB, IQ1_M is 21.8 GB, IQ2_XXS is 25.0 GB, IQ2_XS is 27.9 GB, IQ2_S is 29.2 GB, IQ2_M is 31.8 GB and 8 more.

What context length does BigWeave v26 95b support?

The GGUF header lists a trained context length of 32,764 tokens (32K). The KV cache grows with the context you use: about 3.7 GB at 8K and 14.8 GB at 32K.

Where can I download BigWeave v26 95b GGUF?

The files are on Hugging Face in the mradermacher/BigWeave-v26-95b-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 BigWeave v26 95b use?

Hugging Face lists the license as unknown. 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 BigWeave v26 95b on 8 GB VRAM?

Use the IQ1_S quantization; it requires about 24.1 GB of VRAM at 8 k context, so 8 GB is insufficient.

Does this model support vision tasks?

No, the model has no vision capabilities.

What prompting formats are supported?

Chatml, Mistral, and Vicuna prompting formats are supported.

Other GGUFs of BigWeave-v26-95b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Bigweave models

All Bigweave →

Other large models

All large models →