DU

Dumbstral 169B i1

DumbstralGGUF by mradermacherUpdated 2024-11-21
Download on Hugging Face
Parameters170B
Context128K
Layers122
Architecturellama
Smallest quant35.8 GB
Quick answer

Dumbstral 169B i1 needs about 43.8 GB of memory at IQ1_M (a 39.2 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 4 quants, from 35.8 GB (IQ1_S) to 49.9 GB (IQ2_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 16.4 GB.

Dumbstral 169B i1 is a 170B-parameter Dumbstral model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 4 quant files, from 35.8 GB (IQ1_S) to 49.9 GB (IQ2_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S35.8 GB 40.4 GB
Too big Get file →
IQ1_M39.2 GB 43.8 GB
Too big Get file →
IQ2_XXS44.8 GB 49.4 GB
Too big Get file →
IQ2_XS49.9 GB 54.5 GB
Too big Get file →

What GPU do you need for Dumbstral 169B 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: 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 IQ1_M (39.2 GB file, about 43.8 GB in use).

Which Dumbstral 169B i1 quant should you choose?

IQ1_M (39.2 GB) is the middle option in this repository. 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.

If memory is tight, the smallest file is IQ1_S at 35.8 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
Parameters170B
Layers122
Trained context131,072 tokens
KV cache (fp16)488 KB per token

Source

Quantized bymradermacher
FamilyDumbstral
Licenseother
Downloads (HF)77
Last updated2024-11-21

Frequently asked questions about Dumbstral 169B i1

How much VRAM does Dumbstral 169B i1 need?

About 43.8 GB at IQ1_M with an 8K context window. That is the 39.2 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 Dumbstral 169B i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 40.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Dumbstral 169B i1 GGUF?

It depends on the quant: IQ1_S is 35.8 GB, IQ1_M is 39.2 GB, IQ2_XXS is 44.8 GB, IQ2_XS is 49.9 GB.

What context length does Dumbstral 169B i1 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.1 GB at 8K and 16.4 GB at 32K.

Where can I download Dumbstral 169B i1 GGUF?

The files are on Hugging Face in the mradermacher/Dumbstral-169B-i1-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 Dumbstral 169B i1 use?

Hugging Face lists the license as other. 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 mradermacher

All by mradermacher →

More Dumbstral models

All Dumbstral →

Other large models

All large models →