BA

weyaxi_bagel-hermes-2x34b

BagelGGUF by TheBlokeUpdated 2024-01-13
Download on Hugging Face
Parameters60.8B
Context195K
Layers60
Architecturellama
Smallest quant22.3 GB
Quick answer

weyaxi_bagel-hermes-2x34b 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 7 quants, from 22.3 GB (Q2_K) 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: 60.8B parameter MOE model in GGUF format

Bagel-Hermes-2x34b is a 60.8B parameter mixture of experts model based on the Bagel family. It supports tool usage and is available in multiple GGUF quantizations. The model was trained on a context of 200000 tokens.

Good at

  • Tool usage
  • Large context handling
  • Mixture of experts

Limits

  • No vision support
  • License is other
  • Requires high VRAM for larger quants

Best for

  • Chat assistants needing tool integration
  • Long‑form content generation
  • Complex reasoning tasks

Who it’s for. Developers and researchers who need a large‑parameter LLM with tool‑use capability and are comfortable managing quantized GGUF files. It is suitable for local deployment with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K22.3 GB 24.8 GB
Too big Get file →
Q3_K_M29.3 GB 31.8 GB
Too big Get file →
Q4_034.3 GB 36.8 GB
Too big Get file →
Q4_K_M36.7 GB 39.2 GB
Too big Get file →
Q5_041.9 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 Q2_K (22.33 GB file, ~24.8 GB memory at 8 k context). For 12 GB VRAM, Q3_K_M (29.25 GB file, ~31.8 GB memory). For 16 GB VRAM, Q4_0 (34.33 GB file, ~36.8 GB memory). Higher quants require more memory.

What GPU do you need for weyaxi_bagel-hermes-2x34b?

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: the best quant that fits is Q3_K_M (29.3 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 weyaxi_bagel-hermes-2x34b quant should you choose?

Q4_K_M is the usual starting point for weyaxi_bagel-hermes-2x34b: it balances file size and quality well. Here it is a 36.7 GB file.

If memory is tight, the smallest file is Q2_K at 22.3 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

Architecturellama
Parameters60.8B (approximate, mixture of experts)
Layers60
Trained context200,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized byTheBloke
FamilyBagel
Licenseother
Downloads (HF)1,305
Last updated2024-01-13

Frequently asked questions about weyaxi_bagel-hermes-2x34b

How much VRAM does weyaxi_bagel-hermes-2x34b 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 weyaxi_bagel-hermes-2x34b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 24.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of weyaxi_bagel-hermes-2x34b GGUF?

It depends on the quant: Q2_K is 22.3 GB, Q3_K_M is 29.3 GB, Q4_0 is 34.3 GB, Q4_K_M is 36.7 GB, Q5_0 is 41.9 GB, Q5_K_M is 43.1 GB and 1 more.

What context length does weyaxi_bagel-hermes-2x34b 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 weyaxi_bagel-hermes-2x34b GGUF?

The files are on Hugging Face in the TheBloke/Bagel-Hermes-2x34b-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 weyaxi_bagel-hermes-2x34b use?

Hugging Face lists the license as other. 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 this model on 8 GB VRAM?

Yes, using the Q2_K quantization which requires about 24.8 GB of VRAM at 8 k context, but this exceeds 8 GB, so it is not feasible. A smaller quant is needed.

Does this model support vision?

No, the model does not have vision capabilities.

What prompt templates are available?

ChatML, Alpaca (sort of), and Vicuna templates are provided in the repository.

Other GGUFs of Bagel-Hermes-2x34B

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Bagel models

All Bagel →

Other large models

All large models →