Bloomz Mt needs about 76.1 GB of memory at IQ1_M (a 42.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 39.2 GB (IQ1_S) to 48.7 GB (IQ2_XXS).
Bloomz Mt is a 180B-parameter Bloomz model in GGUF format, quantized by mradermacher. Its trained context length is 14K tokens. The repository has 3 quant files, from 39.2 GB (IQ1_S) to 48.7 GB (IQ2_XXS).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 39.2 GB | 72.6 GB | Too big | Get file → | |
| IQ1_M | 42.8 GB | 76.1 GB | Too big | Get file → | |
| IQ2_XXS | 48.7 GB | 82.1 GB | Too big | Get file → |
What GPU do you need for Bloomz Mt?
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 Bloomz Mt quant should you choose?
IQ1_M (42.8 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 39.2 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
Source
Frequently asked questions about Bloomz Mt
How much VRAM does Bloomz Mt need?
About 76.1 GB at IQ1_M with an 8K context window. That is the 42.8 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 Bloomz Mt on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 72.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Bloomz Mt GGUF?
It depends on the quant: IQ1_S is 39.2 GB, IQ1_M is 42.8 GB, IQ2_XXS is 48.7 GB.
What context length does Bloomz Mt support?
The GGUF header lists a trained context length of 14,336 tokens (14K). The KV cache grows with the context you use: about 32.9 GB at 8K and 57.5 GB at 14K.
Where can I download Bloomz Mt GGUF?
The files are on Hugging Face in the mradermacher/bloomz-mt-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 Bloomz Mt use?
Hugging Face lists the license as bigscience-bloom-rail-1.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.