DB

dbrx instruct

DbrxGGUF by mradermacherUpdated 2024-09-16
Download on Hugging Face
Parameters132B
Context32K
Layers40
Architecturedbrx
Smallest quant47.9 GB
Quick answer

dbrx instruct needs about 49.8 GB of memory at Q2_K (a 47.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

dbrx instruct is a 132B-parameter Dbrx model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 1 quant file, from 47.9 GB (Q2_K) to 47.9 GB (Q2_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K47.9 GB 49.8 GB
Too big Get file →

What GPU do you need for dbrx instruct?

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: no quant fits at an 8K context.

Which dbrx instruct quant should you choose?

Q2_K (47.9 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedbrx
Parameters132B (approximate, mixture of experts)
Layers40
Trained context32,768 tokens
KV cache (fp16)160 KB per token

Source

Quantized bymradermacher
FamilyDbrx
Downloads (HF)38
Last updated2024-09-16

Frequently asked questions about dbrx instruct

How much VRAM does dbrx instruct need?

About 49.8 GB at Q2_K with an 8K context window. That is the 47.9 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 dbrx instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 49.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of dbrx instruct GGUF?

It depends on the quant: Q2_K is 47.9 GB.

What context length does dbrx instruct support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download dbrx instruct GGUF?

The files are on Hugging Face in the mradermacher/dbrx-instruct-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 dbrx-instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Dbrx models

All Dbrx →

Other large models

All large models →