BI

BigWeave v31 96b i1

BigweaveGGUF by mradermacherUpdated 2024-12-09
Download on Hugging Face
Parameters96.2B
Context8K
Layers110
Architecturellama
Smallest quant20.7 GB
Quick answer

BigWeave v31 96b i1 needs about 37.2 GB of memory at Q2_K_S (a 33.0 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 14 quants, from 20.7 GB (IQ1_S) to 46.5 GB (Q3_K_M).

BigWeave v31 96b i1 is a 96.2B-parameter Bigweave model in GGUF format, quantized by mradermacher. Its trained context length is 8K tokens. The repository has 14 quant files, from 20.7 GB (IQ1_S) to 46.5 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S20.7 GB 24.9 GB
Too big Get file →
IQ1_M22.6 GB 26.8 GB
Too big Get file →
IQ2_XXS25.8 GB 30.0 GB
Too big Get file →
IQ2_XS28.7 GB 32.9 GB
Too big Get file →
IQ2_S30.1 GB 34.3 GB
Too big Get file →
IQ2_M32.7 GB 36.9 GB
Too big Get file →
Q2_K_S33.0 GB 37.2 GB
Too big Get file →
Q2_K35.7 GB 39.9 GB
Too big Get file →
IQ3_XXS37.2 GB 41.4 GB
Too big Get file →
IQ3_XS39.7 GB 43.9 GB
Too big Get file →
Q3_K_S41.8 GB 46.0 GB
Too big Get file →
IQ3_S41.9 GB 46.1 GB
Too big Get file →
IQ3_M43.3 GB 47.5 GB
Too big Get file →
Q3_K_M46.5 GB 50.7 GB
Too big Get file →

What GPU do you need for BigWeave v31 96b i1?

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_XXS (25.8 GB file, about 30.0 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ3_M (43.3 GB file, about 47.5 GB in use).

Which BigWeave v31 96b i1 quant should you choose?

Q2_K_S (33.0 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 20.7 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
Parameters96.2B
Layers110
Trained context8,192 tokens
KV cache (fp16)440 KB per token

Source

Quantized bymradermacher
FamilyBigweave
Licensellama3
Downloads (HF)205
Last updated2024-12-09

Frequently asked questions about BigWeave v31 96b i1

How much VRAM does BigWeave v31 96b i1 need?

About 37.2 GB at Q2_K_S with an 8K context window. That is the 33.0 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 v31 96b i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 24.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of BigWeave v31 96b i1 GGUF?

It depends on the quant: IQ1_S is 20.7 GB, IQ1_M is 22.6 GB, IQ2_XXS is 25.8 GB, IQ2_XS is 28.7 GB, IQ2_S is 30.1 GB, IQ2_M is 32.7 GB and 8 more.

What context length does BigWeave v31 96b i1 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.7 GB at 8K and 3.7 GB at 8K.

Where can I download BigWeave v31 96b i1 GGUF?

The files are on Hugging Face in the mradermacher/BigWeave-v31-96b-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 v31 96b i1 use?

Hugging Face lists the license as llama3. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of BigWeave-v31-96b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Bigweave models

All Bigweave →

Other large models

All large models →