BA

Bagel Hermes 2x34B i1

BagelGGUF by mradermacherUpdated 2024-06-29
Download on Hugging Face
Parameters60.8B
Context195K
Layers60
Architecturellama
Smallest quant12.8 GB
Quick answer

Bagel Hermes 2x34B i1 needs about 39.2 GB of memory at Q4_K_M (a 36.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 21 quants, from 12.8 GB (IQ1_S) to 49.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

Bagel Hermes 2x34B i1 – 60.8B parameter MOE model

Bagel Hermes 2x34B i1 is a 60.8B parameter mixture of experts model based on the Bagel family. It supports tool usage and is trained with a context of 200000 tokens. The model is released under the apache-2.0 license.

Good at

  • Tool integration
  • Large context handling
  • High parameter count

Limits

  • No vision support
  • Requires large VRAM for higher quants
  • License is apache-2.0

Best for

  • Chatbot with tool calls
  • Long‑form content generation
  • Complex reasoning tasks

Who it’s for. Developers building advanced conversational agents that need tool integration and long‑context support. The model is suitable for research and production environments that can accommodate its memory requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S12.8 GB 15.3 GB
Too big Get file →
IQ1_M14.1 GB 16.6 GB
Too big Get file →
IQ2_XXS16.2 GB 18.7 GB
Too big Get file →
IQ2_XS18.0 GB 20.5 GB
Too big Get file →
IQ2_S18.7 GB 21.2 GB
Too big Get file →
IQ2_M20.4 GB 22.9 GB
Too big Get file →
Q2_K22.4 GB 24.9 GB
Too big Get file →
IQ3_XXS23.5 GB 26.0 GB
Too big Get file →
IQ3_XS25.0 GB 27.5 GB
Too big Get file →
Q3_K_S26.3 GB 28.8 GB
Too big Get file →
IQ3_S26.4 GB 28.9 GB
Too big Get file →
IQ3_M27.1 GB 29.6 GB
Too big Get file →
Q3_K_M29.2 GB 31.8 GB
Too big Get file →
Q3_K_L31.8 GB 34.3 GB
Too big Get file →
IQ4_XS32.5 GB 35.0 GB
Too big Get file →
Q4_034.5 GB 37.0 GB
Too big Get file →
Q4_K_S34.6 GB 37.1 GB
Too big Get file →
Q4_K_M36.7 GB 39.2 GB
Too big Get file →
Q5_K_S41.9 GB 44.4 GB
Too big Get file →
Q5_K_M43.1 GB 45.6 GB
Too big Get file →
Q6_K49.9 GB 52.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (12.8 GB file, 15.3 GB memory at 8 k context). For 16 GB VRAM, IQ2_XS (17.99 GB file, 20.5 GB memory) or Q2_K (22.39 GB file, 24.9 GB memory). For 32 GB VRAM, Q4_K_M (36.66 GB file, 39.2 GB memory) or Q5_K_M (43.08 GB file, 45.6 GB memory).

What GPU do you need for Bagel Hermes 2x34B 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_S (12.8 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ2_M (20.4 GB file, about 22.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q3_K_M (29.2 GB file, about 31.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q5_K_M (43.1 GB file, about 45.6 GB in use).

Which Bagel Hermes 2x34B i1 quant should you choose?

Q4_K_M is the usual starting point for Bagel Hermes 2x34B i1: it balances file size and quality well. Here it is a 36.7 GB file.

If memory is tight, the smallest file is IQ1_S at 12.8 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
Parameters60.8B (approximate, mixture of experts)
Layers60
Trained context200,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized bymradermacher
FamilyBagel
Licenseapache-2.0
Downloads (HF)1,186
Last updated2024-06-29

Frequently asked questions about Bagel Hermes 2x34B i1

How much VRAM does Bagel Hermes 2x34B i1 need?

About 39.2 GB at Q4_K_M with an 8K context window. That is the 36.7 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 Bagel Hermes 2x34B i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Bagel Hermes 2x34B i1 GGUF?

It depends on the quant: IQ1_S is 12.8 GB, IQ1_M is 14.1 GB, IQ2_XXS is 16.2 GB, IQ2_XS is 18.0 GB, IQ2_S is 18.7 GB, IQ2_M is 20.4 GB and 15 more.

What context length does Bagel Hermes 2x34B i1 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 Hermes 2x34B i1 GGUF?

The files are on Hugging Face in the mradermacher/Bagel-Hermes-2x34B-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 Bagel Hermes 2x34B i1 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 Hermes 2x34B i1 on 8 GB VRAM?

Use the IQ1_S quant, which requires 15.3 GB memory at 8 k context. 8 GB VRAM is insufficient for this model.

Does Bagel Hermes 2x34B i1 support vision?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of Bagel-Hermes-2x34B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Bagel models

All Bagel →

Other large models

All large models →