BI

BigWeave v27 95b

BigweaveGGUF by RichardErkhovUpdated 2024-10-28
Download on Hugging Face
Parameters96.4B
Context32K
Layers112
Architecturellama
Smallest quant35.4 GB
Quick answer

BigWeave v27 95b needs about 62.0 GB of memory at Q4_K_M (a 57.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 22 quants, from 35.4 GB (Q2_K) to 102.4 GB (Q8_0).

BigWeave v27 95b is a 96.4B-parameter Bigweave model in GGUF format, quantized by RichardErkhov. Its trained context length is 32K tokens. The repository has 22 quant files, from 35.4 GB (Q2_K) to 102.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K35.4 GB 39.7 GB
Too big Get file →
IQ3_XS39.4 GB 43.7 GB
Too big Get file →
Q3_K_S41.5 GB (2 parts) 45.8 GB
Too big Get file →
IQ3_S41.6 GB (2 parts) 45.9 GB
Too big Get file →
IQ3_M43.1 GB (2 parts) 47.3 GB
Too big Get file →
Q3_K46.3 GB (2 parts) 50.6 GB
Too big Get file →
Q3_K_M46.3 GB (2 parts) 50.6 GB
Too big Get file →
Q3_K_L50.5 GB (2 parts) 54.7 GB
Too big Get file →
IQ4_XS51.9 GB (2 parts) 56.2 GB
Too big Get file →
Q4_054.3 GB (2 parts) 58.5 GB
Too big Get file →
Q4_K_S54.7 GB (2 parts) 58.9 GB
Too big Get file →
IQ4_NL54.8 GB (2 parts) 59.1 GB
Too big Get file →
Q4_K57.8 GB (2 parts) 62.0 GB
Too big Get file →
Q4_K_M57.8 GB (2 parts) 62.0 GB
Too big Get file →
Q4_160.3 GB (2 parts) 64.5 GB
Too big Get file →
Q5_066.3 GB (2 parts) 70.5 GB
Too big Get file →
Q5_K_S66.3 GB (2 parts) 70.5 GB
Too big Get file →
Q5_K68.1 GB (2 parts) 72.4 GB
Too big Get file →
Q5_K_M68.1 GB (2 parts) 72.4 GB
Too big Get file →
Q5_172.3 GB (2 parts) 76.6 GB
Too big Get file →
Q6_K79.0 GB (2 parts) 83.3 GB
Too big Get file →
Q8_0102.4 GB (3 parts) 106.6 GB
Too big Get file →

What GPU do you need for BigWeave v27 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: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is IQ3_M (43.1 GB file, about 47.3 GB in use).

Which BigWeave v27 95b quant should you choose?

Q4_K_M is the usual starting point for BigWeave v27 95b: it balances file size and quality well. Here it is a 57.8 GB file.

The Q8_0 file is 102.4 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 Q2_K at 35.4 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
Parameters96.4B
Layers112
Trained context32,764 tokens
KV cache (fp16)448 KB per token

Source

Quantized byRichardErkhov
FamilyBigweave
Licenseunknown
Downloads (HF)6
Last updated2024-10-28

Frequently asked questions about BigWeave v27 95b

How much VRAM does BigWeave v27 95b need?

About 62.0 GB at Q4_K_M with an 8K context window. That is the 57.8 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 v27 95b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 39.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of BigWeave v27 95b GGUF?

It depends on the quant: Q2_K is 35.4 GB, IQ3_XS is 39.4 GB, Q3_K_S is 41.5 GB, IQ3_S is 41.6 GB, IQ3_M is 43.1 GB, Q3_K is 46.3 GB and 16 more.

What context length does BigWeave v27 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 3.8 GB at 8K and 15.0 GB at 32K.

Where can I download BigWeave v27 95b GGUF?

The files are on Hugging Face in the RichardErkhov/llmixer_-_BigWeave-v27-95b-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 v27 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.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Bigweave models

All Bigweave →

Other large models

All large models →