bagel dpo 34b v0.5 iMat needs about 21.0 GB of memory at IQ4_XS (a 18.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 10.3 GB (IQ2_XS) to 36.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
bagel dpo 34b v0.5 iMat is a 34.4B-parameter Bagel model in GGUF format, quantized by dranger003. Its trained context length is 195K tokens. The repository has 6 quant files, from 10.3 GB (IQ2_XS) to 36.5 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XS | 10.3 GB | 12.8 GB | Too big | Get file → | |
| IQ3_XS | 14.2 GB | 16.7 GB | Too big | Get file → | |
| IQ4_XS | 18.5 GB | 21.0 GB | Too big | Get file → | |
| Q5_K | 24.3 GB | 26.8 GB | Too big | Get file → | |
| Q6_K | 28.2 GB | 30.7 GB | Too big | Get file → | |
| Q8_0 | 36.5 GB | 39.1 GB | Too big | Get file → |
What GPU do you need for bagel dpo 34b v0.5 iMat?
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 IQ2_XS (10.3 GB file, about 12.8 GB in use).
- 24 GB VRAM: the best quant that fits is IQ4_XS (18.5 GB file, about 21.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (28.2 GB file, about 30.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (36.5 GB file, about 39.1 GB in use).
Which bagel dpo 34b v0.5 iMat quant should you choose?
IQ4_XS (18.5 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is IQ2_XS at 10.3 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 bagel dpo 34b v0.5 iMat
How much VRAM does bagel dpo 34b v0.5 iMat need?
About 21.0 GB at IQ4_XS with an 8K context window. That is the 18.5 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 bagel dpo 34b v0.5 iMat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of bagel dpo 34b v0.5 iMat GGUF?
It depends on the quant: IQ2_XS is 10.3 GB, IQ3_XS is 14.2 GB, IQ4_XS is 18.5 GB, Q5_K is 24.3 GB, Q6_K is 28.2 GB, Q8_0 is 36.5 GB.
What context length does bagel dpo 34b v0.5 iMat support?
The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.
Where can I download bagel dpo 34b v0.5 iMat GGUF?
The files are on Hugging Face in the dranger003/bagel-dpo-34b-v0.5-iMat.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 bagel dpo 34b v0.5 iMat use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.