CW

cwm Q6 K

CwmGGUF by abhijithmallyaUpdated 2025-09-26
Download on Hugging Face
Parameters32.6B
Context128K
Layers64
Architecturellama
Smallest quant26.7 GB
Quick answer

cwm Q6 K needs about 29.4 GB of memory at Q6_K (a 26.7 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

cwm Q6 K is a 32.6B-parameter Cwm model in GGUF format, quantized by abhijithmallya. Its trained context length is 128K tokens. The repository has 1 quant file, from 26.7 GB (Q6_K) to 26.7 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K26.7 GB 29.4 GB
Too big Get file →

What GPU do you need for cwm Q6 K?

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 Q6_K (26.7 GB file, about 29.4 GB in use).

Which cwm Q6 K quant should you choose?

Q6_K (26.7 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters32.6B
Layers64
Trained context131,072 tokens
KV cache (fp16)256 KB per token

Source

Quantized byabhijithmallya
FamilyCwm
Base modelfacebook/cwm
Downloads (HF)25
Last updated2025-09-26

Frequently asked questions about cwm Q6 K

How much VRAM does cwm Q6 K need?

About 29.4 GB at Q6_K with an 8K context window. That is the 26.7 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 cwm Q6 K on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 29.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of cwm Q6 K GGUF?

It depends on the quant: Q6_K is 26.7 GB.

What context length does cwm Q6 K support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download cwm Q6 K GGUF?

The files are on Hugging Face in the abhijithmallya/cwm-Q6_K-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 cwm Q6 K use?

Hugging Face lists the license as fair-noncommercial-research-license. 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 cwm

Similar models

Browse all →

More from abhijithmallya

All by abhijithmallya →

More Cwm models

All Cwm →

Other medium models

All medium models →