BO

Boundary Hermes Chat 2x7B MoE

BoundaryGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters12.9B
Context32K
Layers32
Architecturellama
Smallest quant4.8 GB
Quick answer

Boundary Hermes Chat 2x7B MoE needs about 9.4 GB of memory at Q4_K_M (a 7.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 4.8 GB (Q2_K) to 13.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Boundary Hermes Chat 2x7B MoE – a 12.9B llama-based mixture of experts model

Boundary Hermes Chat 2x7B MoE is a 12.9B parameter llama architecture model with a 32768 token context window. It is a mixture of experts and supports tool usage. The model is released under the apache-2.0 license.

Good at

  • Tool usage
  • Large context handling
  • Mixture of experts architecture

Limits

  • No vision support
  • Requires high VRAM for larger quants
  • No active parameter count provided

Best for

  • Chat applications needing long context
  • Tool‑enabled workflows
  • Research on MoE models

Who it’s for. Developers building chatbots that require extended context and tool integration. Researchers interested in mixture‑of‑experts architectures may also find this model useful.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.8 GB 6.3 GB
Fits Get file →
IQ3_XS5.3 GB 6.9 GB
Fits Get file →
Q3_K_S5.6 GB 7.2 GB
Fits Get file →
IQ3_S5.6 GB 7.2 GB
Fits Get file →
IQ3_M5.7 GB 7.3 GB
Tight Get file →
Q3_K_M6.2 GB 7.8 GB
Tight Get file →
Q3_K_L6.7 GB 8.3 GB
Too big Get file →
IQ4_XS7.0 GB 8.6 GB
Too big Get file →
Q4_K_S7.3 GB 8.9 GB
Too big Get file →
Q4_K_M7.8 GB 9.4 GB
Too big Get file →
Q5_K_S8.9 GB 10.4 GB
Too big Get file →
Q5_K_M9.1 GB 10.7 GB
Too big Get file →
Q6_K10.6 GB 12.1 GB
Too big Get file →
Q8_013.7 GB 15.3 GB
Too big Get file →

For 8 GB VRAM, the Q2_K (4.76 GB) or IQ3_XS (5.31 GB) quants are suitable, estimating 6.3 GB or 6.9 GB memory at 8 k context. If 12 GB VRAM is available, Q4_K_M (7.78 GB) or Q5_K_S (8.87 GB) provide a balance of size and performance. Higher quants such as Q6_K (10.57 GB) or Q8_0 (13.69 GB) require more than 15 GB VRAM.

What GPU do you need for Boundary Hermes Chat 2x7B MoE?

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: the best quant that fits is Q3_K_M (6.2 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_M (9.1 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.7 GB file, about 15.3 GB in use).

Which Boundary Hermes Chat 2x7B MoE quant should you choose?

Q4_K_M is the usual starting point for Boundary Hermes Chat 2x7B MoE: it balances file size and quality well. Here it is a 7.8 GB file.

The Q8_0 file is 13.7 GB, about 1.8 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 Q2_K at 4.8 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
Parameters12.9B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyBoundary
Licenseapache-2.0
Downloads (HF)1,466
Last updated2024-05-06

Frequently asked questions about Boundary Hermes Chat 2x7B MoE

How much VRAM does Boundary Hermes Chat 2x7B MoE need?

About 9.4 GB at Q4_K_M with an 8K context window. That is the 7.8 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 Boundary Hermes Chat 2x7B MoE on an 8 GB GPU?

Yes, with Q3_K_M: the 6.2 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Boundary Hermes Chat 2x7B MoE GGUF?

It depends on the quant: Q2_K is 4.8 GB, IQ3_XS is 5.3 GB, Q3_K_S is 5.6 GB, IQ3_S is 5.6 GB, IQ3_M is 5.7 GB, Q3_K_M is 6.2 GB and 8 more.

What context length does Boundary Hermes Chat 2x7B MoE 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 Boundary Hermes Chat 2x7B MoE GGUF?

The files are on Hugging Face in the mradermacher/Boundary-Hermes-Chat-2x7B-MoE-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 Boundary Hermes Chat 2x7B MoE 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 this model on 8 GB VRAM?

Yes, the Q2_K and IQ3_XS quants fit within 8 GB VRAM, with estimated memory usage of 6.3 GB and 6.9 GB respectively at 8 k context.

Does this model support vision?

No, the model does not provide vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Boundary models

All Boundary →

Other medium models

All medium models →