AI

aixsatoshi Ex karakuri 8x12B chat v1

AixsatoshiGGUF by mmngaUpdated 2024-05-19
Download on Hugging Face
Parameters81.5B
Context32K
Layers56
Architecturellama
Smallest quant17.1 GB
Quick answer

aixsatoshi Ex karakuri 8x12B chat v1 needs about 36.1 GB of memory at IQ3_XS (a 33.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 18 quants, from 17.1 GB (IQ1_S) to 46.7 GB (Q4_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

81.5B‑parameter Llama‑style chat model

aixsatoshi Ex karakuri 8x12B chat v1 is an 81.5B‑parameter Llama architecture model. It supports a 32768‑token context window and is released under the apache‑2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • Large context handling
  • High‑parameter capacity
  • Apache‑2.0 licensed

Limits

  • No vision support
  • Requires large VRAM for full precision
  • No mixture‑of‑experts details

Best for

  • Long‑form dialogue
  • Complex reasoning tasks
  • Large‑scale text generation

Who it’s for. Developers needing a high‑parameter chat model with extended context. Suitable for research or production environments that can accommodate the memory demands.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S17.1 GB 19.5 GB
Too big Get file →
IQ1_M18.9 GB 21.3 GB
Too big Get file →
IQ2_XXS21.9 GB 24.2 GB
Too big Get file →
IQ2_XS24.3 GB 26.6 GB
Too big Get file →
IQ2_S24.6 GB 27.0 GB
Too big Get file →
IQ2_M27.0 GB 29.4 GB
Too big Get file →
Q2_K30.2 GB 32.6 GB
Too big Get file →
IQ3_XXS31.8 GB 34.2 GB
Too big Get file →
IQ3_XS33.7 GB 36.1 GB
Too big Get file →
Q3_K_S35.6 GB 38.0 GB
Too big Get file →
IQ3_S35.6 GB 38.0 GB
Too big Get file →
IQ3_M37.4 GB 39.8 GB
Too big Get file →
Q3_K_M39.3 GB 41.7 GB
Too big Get file →
Q3_K_L42.2 GB 44.5 GB
Too big Get file →
IQ4_XS43.8 GB 46.1 GB
Too big Get file →
Q4_046.1 GB 48.5 GB
Too big Get file →
IQ4_NL46.3 GB 48.6 GB
Too big Get file →
Q4_K_S46.7 GB 49.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (17.08 GB file, 19.5 GB memory). For 12 GB VRAM, IQ1_M (18.88 GB file, 21.3 GB memory). For 16 GB VRAM, IQ2_XXS (21.87 GB file, 24.2 GB memory).

What GPU do you need for aixsatoshi Ex karakuri 8x12B chat v1?

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: the best quant that fits is IQ1_M (18.9 GB file, about 21.3 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ2_M (27.0 GB file, about 29.4 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ4_XS (43.8 GB file, about 46.1 GB in use).

Which aixsatoshi Ex karakuri 8x12B chat v1 quant should you choose?

IQ3_XS (33.7 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 17.1 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
Parameters81.5B (approximate, mixture of experts)
Layers56
Trained context32,768 tokens
KV cache (fp16)224 KB per token

Source

Quantized bymmnga
Licenseapache-2.0
Downloads (HF)2,843
Last updated2024-05-19

Frequently asked questions about aixsatoshi Ex karakuri 8x12B chat v1

How much VRAM does aixsatoshi Ex karakuri 8x12B chat v1 need?

About 36.1 GB at IQ3_XS with an 8K context window. That is the 33.7 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 aixsatoshi Ex karakuri 8x12B chat v1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of aixsatoshi Ex karakuri 8x12B chat v1 GGUF?

It depends on the quant: IQ1_S is 17.1 GB, IQ1_M is 18.9 GB, IQ2_XXS is 21.9 GB, IQ2_XS is 24.3 GB, IQ2_S is 24.6 GB, IQ2_M is 27.0 GB and 12 more.

What context length does aixsatoshi Ex karakuri 8x12B chat v1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download aixsatoshi Ex karakuri 8x12B chat v1 GGUF?

The files are on Hugging Face in the mmnga/aixsatoshi-Ex-karakuri-8x12B-chat-v1-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 aixsatoshi Ex karakuri 8x12B chat v1 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?

Use the IQ1_S quantization; it requires approximately 19.5 GB memory at 8k context.

Does the model support vision inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Similar models

Browse all →

More from mmnga

All by mmnga →

More Aixsatoshi models

All Aixsatoshi →

Other large models

All large models →