BA

Bagel Dpo 8x7b v0.2

BagelGGUF by bartowskiUpdated 2024-12-02
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant10.8 GB
Quick answer

Bagel Dpo 8x7b v0.2 needs about 30.0 GB of memory at Q4_K_M (a 28.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 10.8 GB (IQ1_M) to 49.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Bagel Dpo 8x7b v0.2 – a 46.7B parameter mixtral fine‑tune

Bagel Dpo 8x7b v0.2 is a 46.7B parameter model based on mixtral-8x7b-v0.1. It is fine‑tuned with SFT and DPO and supports coding and roleplay tasks. The model is released under the apache-2.0 license.

Good at

  • Coding tasks
  • Roleplay scenarios
  • Long‑form instruction following

Limits

  • No vision support
  • Large VRAM requirement for higher quants
  • Requires 32768 token context

Best for

  • Developers building code assistants
  • Chatbot creators needing roleplay
  • Researchers testing instruction fine‑tuning

Who it’s for. This model is suited for users who need a large, instruction‑tuned LLM with strong coding and roleplay capabilities. It is ideal for developers and researchers who can provide sufficient GPU memory for the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M10.8 GB 12.4 GB
Too big Get file →
IQ2_XXS12.6 GB 14.1 GB
Too big Get file →
IQ2_XS13.9 GB 15.5 GB
Too big Get file →
IQ2_M15.5 GB 17.1 GB
Too big Get file →
Q2_K17.3 GB 18.9 GB
Too big Get file →
Q2_K_L17.4 GB 19.0 GB
Too big Get file →
IQ3_XXS18.2 GB 19.8 GB
Too big Get file →
Q3_K_S20.4 GB 22.0 GB
Too big Get file →
IQ3_M21.4 GB 23.0 GB
Too big Get file →
Q3_K_M22.5 GB 24.1 GB
Too big Get file →
Q3_K_L24.2 GB 25.7 GB
Too big Get file →
Q3_K_XL24.3 GB 25.9 GB
Too big Get file →
IQ4_XS25.1 GB 26.7 GB
Too big Get file →
Q4_026.4 GB 28.0 GB
Too big Get file →
Q4_026.4 GB 28.0 GB
Too big Get file →
Q4_026.4 GB 28.0 GB
Too big Get file →
IQ4_NL26.5 GB 28.1 GB
Too big Get file →
Q4_026.6 GB 28.1 GB
Too big Get file →
Q4_K_S26.7 GB 28.3 GB
Too big Get file →
Q4_K_M28.4 GB 30.0 GB
Too big Get file →
Q5_K_S32.2 GB 33.8 GB
Too big Get file →
Q5_K_M33.2 GB 34.8 GB
Too big Get file →
Q6_K38.4 GB 40.0 GB
Too big Get file →
Q8_049.6 GB 51.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_M (10.85 GB file, 12.4 GB memory at 8k context). For 12 GB VRAM, IQ2_XXS (12.56 GB file, 14.1 GB memory). For 16 GB VRAM, IQ2_XS (13.92 GB file, 15.5 GB memory). Higher quants require proportionally more VRAM.

What GPU do you need for Bagel Dpo 8x7b v0.2?

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 (13.9 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ3_M (21.4 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (28.4 GB file, about 30.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (38.4 GB file, about 40.0 GB in use).

Which Bagel Dpo 8x7b v0.2 quant should you choose?

Q4_K_M is the usual starting point for Bagel Dpo 8x7b v0.2: it balances file size and quality well. Here it is a 28.4 GB file.

The Q8_0 file is 49.6 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ1_M at 10.8 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

Architecturellama
Parameters46.7B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bybartowski
FamilyBagel
Licenseapache-2.0
Downloads (HF)1,671
Last updated2024-12-02

Frequently asked questions about Bagel Dpo 8x7b v0.2

How much VRAM does Bagel Dpo 8x7b v0.2 need?

About 30.0 GB at Q4_K_M with an 8K context window. That is the 28.4 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 8x7b v0.2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Bagel Dpo 8x7b v0.2 GGUF?

It depends on the quant: IQ1_M is 10.8 GB, IQ2_XXS is 12.6 GB, IQ2_XS is 13.9 GB, IQ2_M is 15.5 GB, Q2_K is 17.3 GB, Q2_K_L is 17.4 GB and 18 more.

What context length does Bagel Dpo 8x7b v0.2 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Bagel Dpo 8x7b v0.2 GGUF?

The files are on Hugging Face in the bartowski/bagel-dpo-8x7b-v0.2-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 8x7b v0.2 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.

Can I run Bagel Dpo 8x7b v0.2 on 8 GB VRAM?

Use the IQ1_M quant, which requires 12.4 GB memory at 8k context. 8 GB VRAM is insufficient for full model loading.

Does the model support vision tasks?

No, Bagel Dpo 8x7b v0.2 does not have vision capabilities.

What is the maximum context length?

The model supports up to 32768 tokens of context.

Other GGUFs of bagel-dpo-8x7b-v0.2

Similar models

Browse all →

More from bartowski

All by bartowski →

More Bagel models

All Bagel →

Other large models

All large models →