DB

dbrx 16x12b instruct q4 0

DbrxGGUF by phymbertUpdated 2024-04-12
Download on Hugging Face
Parameters132B
Context32K
Layers40
Architecturedbrx
Smallest quant74.2 GB
Quick answer

dbrx 16x12b instruct q4 0 needs about 76.0 GB of memory at Q4_0 (a 74.2 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 16x12b instruct Q4_0 – a 132 B parameter model in GGUF format

The dbrx 16x12b instruct Q4_0 model contains 132 B parameters and is quantized to Q4_0 for use with llama.cpp. It supports a context length of 32768 tokens and is available as a single 74.19 GB GGUF file split into 10 shards.

Good at

  • Large context handling
  • High parameter count
  • Instruction following

Limits

  • Requires 76 GB VRAM at 8 k context
  • No vision support
  • License type is other

Best for

  • Long‑form content generation
  • Complex instruction tasks
  • Large‑context reasoning

Who it’s for. Developers and researchers needing a large‑parameter, high‑context model for instruction‑based tasks. Suitable for environments with ample GPU memory and no vision requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_074.2 GB (10 parts) 76.0 GB
Too big Get file →

For 8 GB VRAM, the Q4_0 quant is the only available option but it requires 76 GB VRAM at 8 k context. If you have 8 GB VRAM, the model cannot be loaded. For larger GPUs, the 74.19 GB file can be used directly.

What GPU do you need for dbrx 16x12b instruct q4 0?

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 16x12b instruct q4 0 quant should you choose?

Q4_0 (74.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

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 byphymbert
FamilyDbrx
Licenseother
Downloads (HF)4,605
Last updated2024-04-12

Frequently asked questions about dbrx 16x12b instruct q4 0

How much VRAM does dbrx 16x12b instruct q4 0 need?

About 76.0 GB at Q4_0 with an 8K context window. That is the 74.2 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 dbrx 16x12b instruct q4 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 76.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of dbrx 16x12b instruct q4 0 GGUF?

It depends on the quant: Q4_0 is 74.2 GB.

What context length does dbrx 16x12b instruct q4 0 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 16x12b instruct q4 0 GGUF?

The files are on Hugging Face in the phymbert/dbrx-16x12b-instruct-q4_0-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 dbrx 16x12b instruct q4 0 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.

Can I run this model on 8 GB VRAM?

No, the model requires 76 GB VRAM at 8 k context, which exceeds 8 GB.

What is the context length of this model?

The model supports 32768 tokens of context.

Is this model vision capable?

No, the model does not support vision.

Similar models

Browse all →

More from phymbert

All by phymbert →

More Dbrx models

All Dbrx →

Other large models

All large models →