HY

HyouKan 3x7B V2 32k

HyoukanGGUF by mradermacherUpdated 2024-05-06
Download on Hugging Face
Parameters18.5B
Context32K
Layers32
Architecturellama
Smallest quant7.0 GB
Quick answer

HyouKan 3x7B V2 32k needs about 12.9 GB of memory at Q4_K_M (a 11.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 14 quants, from 7.0 GB (Q2_K) to 19.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

HyouKan 3x7B V2 32k – 18.5B llama model with 32k context

HyouKan 3x7B V2 32k is a 18.5B parameter llama model with a 32768 token context window. It is released under cc‑by‑nc‑4.0 and supports roleplay. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • Roleplay capabilities
  • Flexible quant options

Limits

  • No vision support
  • cc‑by‑nc‑4.0 license limits commercial use
  • Requires 8k context for memory estimates

Best for

  • Chatbot with long context
  • Creative writing with roleplay
  • Research prototypes needing large context

Who it’s for. Developers and researchers who need a large‑context llama model for non‑commercial projects. The model is suitable for applications that can work within the cc‑by‑nc‑4.0 license constraints.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K7.0 GB 8.5 GB
Too big Get file →
IQ3_XS7.7 GB 9.3 GB
Too big Get file →
Q3_K_S8.2 GB 9.7 GB
Too big Get file →
IQ3_S8.2 GB 9.8 GB
Too big Get file →
IQ3_M8.3 GB 9.9 GB
Too big Get file →
Q3_K_M9.0 GB 10.6 GB
Too big Get file →
Q3_K_L9.8 GB 11.4 GB
Too big Get file →
IQ4_XS10.2 GB 11.7 GB
Too big Get file →
Q4_K_S10.7 GB 12.3 GB
Too big Get file →
Q4_K_M11.4 GB 12.9 GB
Too big Get file →
Q5_K_S12.9 GB 14.5 GB
Too big Get file →
Q5_K_M13.3 GB 14.9 GB
Too big Get file →
Q6_K15.3 GB 16.9 GB
Too big Get file →
Q8_019.8 GB 21.4 GB
Too big Get file →

For 8 GB VRAM use Q2_K (6.96 GB, 8.5 GB memory). For 12 GB VRAM use Q4_K_S (10.7 GB, 12.3 GB memory). For 16 GB VRAM use Q6_K (15.35 GB, 16.9 GB memory). Estimates are approximate.

What GPU do you need for HyouKan 3x7B V2 32k?

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: the best quant that fits is IQ4_XS (10.2 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (13.3 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (19.8 GB file, about 21.4 GB in use).

Which HyouKan 3x7B V2 32k quant should you choose?

Q4_K_M is the usual starting point for HyouKan 3x7B V2 32k: it balances file size and quality well. Here it is a 11.4 GB file.

The Q8_0 file is 19.8 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 Q2_K at 7.0 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
Parameters18.5B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyHyoukan
Downloads (HF)897
Last updated2024-05-06

Frequently asked questions about HyouKan 3x7B V2 32k

How much VRAM does HyouKan 3x7B V2 32k need?

About 12.9 GB at Q4_K_M with an 8K context window. That is the 11.4 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 HyouKan 3x7B V2 32k on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of HyouKan 3x7B V2 32k GGUF?

It depends on the quant: Q2_K is 7.0 GB, IQ3_XS is 7.7 GB, Q3_K_S is 8.2 GB, IQ3_S is 8.2 GB, IQ3_M is 8.3 GB, Q3_K_M is 9.0 GB and 8 more.

What context length does HyouKan 3x7B V2 32k 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 HyouKan 3x7B V2 32k GGUF?

The files are on Hugging Face in the mradermacher/HyouKan-3x7B-V2-32k-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 HyouKan 3x7B V2 32k use?

Hugging Face lists the license as cc-by-nc-4.0. 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, use the Q2_K quant which is 6.96 GB and requires about 8.5 GB VRAM at 8k context.

Is the model suitable for commercial use?

No, the cc‑by‑nc‑4.0 license prohibits commercial use.

Does the model support vision tasks?

No, the model does not have vision capabilities.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Hyoukan models

All Hyoukan →

Other medium models

All medium models →