BI

BigWeave v13 90b i1

BigweaveGGUF by mradermacherUpdated 2024-11-09
Download on Hugging Face
Parameters87.8B
Context4K
Layers102
Architecturellama
Smallest quant18.4 GB
Quick answer

BigWeave v13 90b i1 needs about 39.8 GB of memory at IQ3_XS (a 35.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 17 quants, from 18.4 GB (IQ1_S) to 49.8 GB (Q4_K_S).

BigWeave v13 90b i1 is a 87.8B-parameter Bigweave model in GGUF format, quantized by mradermacher. Its trained context length is 4K tokens. The repository has 17 quant files, from 18.4 GB (IQ1_S) to 49.8 GB (Q4_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S18.4 GB 20.6 GB
Too big Get file →
IQ1_M20.2 GB 22.4 GB
Too big Get file →
IQ2_XXS23.2 GB 25.4 GB
Too big Get file →
IQ2_XS25.8 GB 28.1 GB
Too big Get file →
IQ2_S27.1 GB 29.3 GB
Too big Get file →
IQ2_M29.5 GB 31.7 GB
Too big Get file →
Q2_K32.3 GB 34.5 GB
Too big Get file →
IQ3_XXS33.7 GB 35.9 GB
Too big Get file →
IQ3_XS35.9 GB 38.1 GB
Too big Get file →
Q3_K_S37.8 GB 40.0 GB
Too big Get file →
IQ3_S37.9 GB 40.2 GB
Too big Get file →
IQ3_M39.2 GB 41.4 GB
Too big Get file →
Q3_K_M42.2 GB 44.4 GB
Too big Get file →
Q3_K_L46.0 GB 48.2 GB
Too big Get file →
IQ4_XS46.9 GB 49.1 GB
Too big Get file →
Q4_049.6 GB 51.8 GB
Too big Get file →
Q4_K_S49.8 GB 52.0 GB
Too big Get file →

What GPU do you need for BigWeave v13 90b 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: the best quant that fits is IQ1_S (18.4 GB file, about 22.4 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ2_S (27.1 GB file, about 31.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q3_K_M (42.2 GB file, about 46.1 GB in use).

Which BigWeave v13 90b i1 quant should you choose?

IQ3_XS (35.9 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 18.4 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
Parameters87.8B
Layers102
Trained context4,096 tokens
KV cache (fp16)408 KB per token

Source

Quantized bymradermacher
FamilyBigweave
Downloads (HF)159
Last updated2024-11-09

Frequently asked questions about BigWeave v13 90b i1

How much VRAM does BigWeave v13 90b i1 need?

About 39.8 GB at IQ3_XS with an 8K context window. That is the 35.9 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 v13 90b i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of BigWeave v13 90b i1 GGUF?

It depends on the quant: IQ1_S is 18.4 GB, IQ1_M is 20.2 GB, IQ2_XXS is 23.2 GB, IQ2_XS is 25.8 GB, IQ2_S is 27.1 GB, IQ2_M is 29.5 GB and 11 more.

What context length does BigWeave v13 90b i1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.4 GB at 8K and 1.7 GB at 4K.

Where can I download BigWeave v13 90b i1 GGUF?

The files are on Hugging Face in the mradermacher/BigWeave-v13-90b-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of BigWeave-v13-90b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Bigweave models

All Bigweave →

Other large models

All large models →