MB Zephyria 45b i1 needs about 30.9 GB of memory at Q4_K_M (a 26.7 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 21 quants, from 9.5 GB (IQ1_S) to 36.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 15.2 GB.
MB Zephyria 45b i1 – 44.5B llama model with tool‑use capability
MB Zephyria 45b i1 is a 44.5B parameter llama model quantized for efficient inference. It supports tool usage and has a 131072 token context window. The model is available in multiple GGUF quantizations.
Good at
- Tool‑based task execution
- Long‑form reasoning up to 131072 tokens
- Large‑scale text generation
Limits
- No vision support
- License not specified
- Requires 8k context for memory estimates
Best for
- Developers building tool‑integrated assistants
- Researchers needing long‑context models
- Applications requiring high‑parameter language models
Who it’s for. Engineers and researchers who need a large llama model with tool‑use support and can manage the memory requirements. The model is suitable for environments that can run GGUF files with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 9.5 GB | 13.8 GB | Too big | Get file → | |
| IQ1_M | 10.4 GB | 14.7 GB | Too big | Get file → | |
| IQ2_XXS | 11.9 GB | 16.2 GB | Too big | Get file → | |
| IQ2_XS | 13.2 GB | 17.5 GB | Too big | Get file → | |
| IQ2_S | 14.0 GB | 18.3 GB | Too big | Get file → | |
| IQ2_M | 15.1 GB | 19.4 GB | Too big | Get file → | |
| Q2_K | 16.5 GB | 20.7 GB | Too big | Get file → | |
| IQ3_XXS | 17.1 GB | 21.4 GB | Too big | Get file → | |
| IQ3_XS | 18.3 GB | 22.6 GB | Too big | Get file → | |
| Q3_K_S | 19.2 GB | 23.5 GB | Too big | Get file → | |
| IQ3_S | 19.3 GB | 23.6 GB | Too big | Get file → | |
| IQ3_M | 20.0 GB | 24.3 GB | Too big | Get file → | |
| Q3_K_M | 21.5 GB | 25.8 GB | Too big | Get file → | |
| Q3_K_L | 23.4 GB | 27.7 GB | Too big | Get file → | |
| IQ4_XS | 23.8 GB | 28.1 GB | Too big | Get file → | |
| Q4_0 | 25.2 GB | 29.5 GB | Too big | Get file → | |
| Q4_K_S | 25.3 GB | 29.5 GB | Too big | Get file → | |
| Q4_K_M | 26.7 GB | 30.9 GB | Too big | Get file → | |
| Q5_K_S | 30.6 GB | 34.9 GB | Too big | Get file → | |
| Q5_K_M | 31.4 GB | 35.7 GB | Too big | Get file → | |
| Q6_K | 36.5 GB | 40.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (9.53 GB) or IQ1_M (10.42 GB). If 12 GB VRAM is available, IQ2_XXS (11.89 GB) or IQ2_XS (13.2 GB) are suitable. For 16 GB VRAM, IQ2_S (13.97 GB) or Q2_K (16.46 GB) provide higher quality. Memory estimates are approximate.
What GPU do you need for MB Zephyria 45b 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: the best quant that fits is IQ1_M (10.4 GB file, about 14.7 GB in use).
- 24 GB VRAM: the best quant that fits is IQ3_S (19.3 GB file, about 23.6 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (26.7 GB file, about 30.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (36.5 GB file, about 40.8 GB in use).
Which MB Zephyria 45b i1 quant should you choose?
Q4_K_M is the usual starting point for MB Zephyria 45b i1: it balances file size and quality well. Here it is a 26.7 GB file.
If memory is tight, the smallest file is IQ1_S at 9.5 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 MB Zephyria 45b i1
How much VRAM does MB Zephyria 45b i1 need?
About 30.9 GB at Q4_K_M with an 8K context window. That is the 26.7 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 MB Zephyria 45b i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of MB Zephyria 45b i1 GGUF?
It depends on the quant: IQ1_S is 9.5 GB, IQ1_M is 10.4 GB, IQ2_XXS is 11.9 GB, IQ2_XS is 13.2 GB, IQ2_S is 14.0 GB, IQ2_M is 15.1 GB and 15 more.
What context length does MB Zephyria 45b 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 3.8 GB at 8K and 15.2 GB at 32K.
Where can I download MB Zephyria 45b i1 GGUF?
The files are on Hugging Face in the mradermacher/MB-Zephyria-45b-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run MB Zephyria 45b i1 on 8 GB VRAM?
Yes, the IQ1_S quantization is 9.53 GB and requires about 13.8 GB of VRAM at 8k context, which is close to 8 GB but may need lower context or more VRAM.
Does MB Zephyria 45b i1 support vision tasks?
No, the model does not have vision capabilities.
What is the context length of MB Zephyria 45b i1?
The model supports a context length of 131072 tokens.