DB

dbrx instruct i1

DbrxGGUF by mradermacherUpdated 2024-09-19
Download on Hugging Face
Parameters132B
Context32K
Layers40
Architecturedbrx
Smallest quant26.9 GB
Quick answer

dbrx instruct i1 needs about 40.4 GB of memory at IQ2_XS (a 38.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 7 quants, from 26.9 GB (IQ1_S) to 47.9 GB (Q2_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

dbrx instruct i1 is a 132B-parameter Dbrx model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 7 quant files, from 26.9 GB (IQ1_S) to 47.9 GB (Q2_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S26.9 GB 28.7 GB
Too big Get file →
IQ1_M29.8 GB 31.6 GB
Too big Get file →
IQ2_XXS34.6 GB 36.5 GB
Too big Get file →
IQ2_XS38.5 GB 40.4 GB
Too big Get file →
IQ2_S39.3 GB 41.2 GB
Too big Get file →
IQ2_M43.2 GB 45.0 GB
Too big Get file →
Q2_K47.9 GB 49.8 GB
Too big Get file →

What GPU do you need for dbrx instruct 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: the best quant that fits is IQ1_M (29.8 GB file, about 31.6 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ2_M (43.2 GB file, about 45.0 GB in use).

Which dbrx instruct i1 quant should you choose?

IQ2_XS (38.5 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 26.9 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

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

Source

Quantized bymradermacher
FamilyDbrx
Downloads (HF)260
Last updated2024-09-19

Frequently asked questions about dbrx instruct i1

How much VRAM does dbrx instruct i1 need?

About 40.4 GB at IQ2_XS with an 8K context window. That is the 38.5 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 i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of dbrx instruct i1 GGUF?

It depends on the quant: IQ1_S is 26.9 GB, IQ1_M is 29.8 GB, IQ2_XXS is 34.6 GB, IQ2_XS is 38.5 GB, IQ2_S is 39.3 GB, IQ2_M is 43.2 GB and 1 more.

What context length does dbrx instruct i1 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 i1 GGUF?

The files are on Hugging Face in the mradermacher/dbrx-instruct-i1-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 →