XL

CrystalCall v2 Poincare 7L 91M

XlamGGUF by DuoNeuralUpdated 2026-10-28
Download on Hugging Face
Parameters91M
Context512
Layers—
Architecturecdm
Smallest quant0.1 GB
Quick answer

CrystalCall v2 Poincare 7L 91M needs about 0.6 GB of memory at Q8_0 (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.1 GB (Q8_0) to 0.4 GB (F32).

CrystalCall v2 Poincare 7L 91M is a 91M-parameter Xlam model in GGUF format, quantized by DuoNeural. Its trained context length is 512 tokens. The repository has 2 quant files, from 0.1 GB (Q8_0) to 0.4 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.1 GB 0.6 GB
Fits Get file →
F320.4 GB 0.9 GB
Fits Get file →

What GPU do you need for CrystalCall v2 Poincare 7L 91M?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is F32 (0.4 GB file, about 0.9 GB in use).

Which CrystalCall v2 Poincare 7L 91M quant should you choose?

Q8_0 (0.1 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturecdm
Parameters91M
Trained context512 tokens

Source

Quantized byDuoNeural
FamilyXlam
Licenseapache-2.0
Downloads (HF)258
Last updated2026-10-28

Frequently asked questions about CrystalCall v2 Poincare 7L 91M

How much VRAM does CrystalCall v2 Poincare 7L 91M need?

About 0.6 GB at Q8_0 with an 8K context window. That is the 0.1 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 CrystalCall v2 Poincare 7L 91M on an 8 GB GPU?

Yes, with F32: the 0.4 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of CrystalCall v2 Poincare 7L 91M GGUF?

It depends on the quant: Q8_0 is 0.1 GB, F32 is 0.4 GB.

What context length does CrystalCall v2 Poincare 7L 91M support?

The GGUF header lists a trained context length of 512 tokens (512).

Where can I download CrystalCall v2 Poincare 7L 91M GGUF?

The files are on Hugging Face in the DuoNeural/CrystalCall-v2-Poincare-7L-91M repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does CrystalCall v2 Poincare 7L 91M use?

Hugging Face lists the license as apache-2.0. 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 xLAM-1b-fc-r

Similar models

Browse all →

More from DuoNeural

All by DuoNeural →

More Xlam models

All Xlam →

Other tiny models

All tiny models →