MO

cr-model

ModelGGUF by tastypearUpdated 2024-07-17
Download on Hugging Face
Parameters14.2B
Context32K
Layers40
Architectureqwen2
Smallest quant9.2 GB
Quick answer

cr-model needs about 16.4 GB of memory at Q4_K_M (a 9.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 9.2 GB (Q4_K_M) to 28.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 26.8 GB.

cr-model is a 14.2B-parameter Model model in GGUF format, quantized by tastypear. Its trained context length is 32K tokens. The repository has 5 quant files, from 9.2 GB (Q4_K_M) to 28.3 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M9.2 GB 16.4 GB
Too big Get file →
Q5_K_M10.5 GB 17.7 GB
Too big Get file →
Q6_K12.3 GB 19.5 GB
Too big Get file →
Q8_015.1 GB 22.3 GB
Too big Get file →
F1628.3 GB 35.6 GB
Too big Get file →

What GPU do you need for cr-model?

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 Q8_0 (15.1 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (15.1 GB file, about 22.3 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (28.3 GB file, about 35.6 GB in use).

Which cr-model quant should you choose?

Q4_K_M is the usual starting point for cr-model: it balances file size and quality well. Here it is a 9.2 GB file.

The Q8_0 file is 15.1 GB, about 1.6 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters14.2B
Layers40
Trained context32,768 tokens
KV cache (fp16)800 KB per token

Source

Quantized bytastypear
FamilyModel
Downloads (HF)200
Last updated2024-07-17

Frequently asked questions about cr-model

How much VRAM does cr-model need?

About 16.4 GB at Q4_K_M with an 8K context window. That is the 9.2 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 cr-model on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of cr-model GGUF?

It depends on the quant: Q4_K_M is 9.2 GB, Q5_K_M is 10.5 GB, Q6_K is 12.3 GB, Q8_0 is 15.1 GB, F16 is 28.3 GB.

What context length does cr-model support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 6.7 GB at 8K and 26.8 GB at 32K.

Where can I download cr-model GGUF?

The files are on Hugging Face in the tastypear/TwT-6-cr-model-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 cr-model use?

Hugging Face lists the license as cc-by-nc-4.0. 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 tastypear

All by tastypear →

More Model models

All Model →

Other medium models

All medium models →