Llama 3 ELYZA JP 8B Heretic needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 14 quants, from 3.5 GB (IQ3_XS) to 16.1 GB (F16).
Llama 3 ELYZA JP 8B Heretic – a Japanese‑focused 8B Llama model
Llama 3 ELYZA JP 8B Heretic is an 8.03 billion parameter Llama model fine‑tuned for Japanese usage. It was abliterated with Heretic to reduce harmful content. The model supports a 8192 token context window.
Good at
- Japanese language generation
- Instruction following in Japanese
- Reduced harmful content after abliterating
Limits
- No vision support
- License is llama3, no commercial use without permission
- Large memory requirement for higher precision quants
Best for
- Japanese content creation
- Japanese chatbot applications
- Japanese text summarization
Who it’s for. Developers building Japanese language applications who need a large, instruction‑tuned Llama model with reduced harmful behavior. The model is suitable for research and non‑commercial use under the llama3 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XS | 3.5 GB | 5.1 GB | Fits | Get file → | |
| Q3_K_S | 3.7 GB | 5.2 GB | Fits | Get file → | |
| IQ3_M | 3.8 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_M | 4.0 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_L | 4.3 GB | 5.9 GB | Fits | Get file → | |
| IQ4_XS | 4.5 GB | 6.1 GB | Fits | Get file → | |
| Q4_K_S | 4.7 GB | 6.3 GB | Fits | Get file → | |
| IQ4_NL | 4.7 GB | 6.3 GB | Fits | Get file → | |
| Q4_K_M | 4.9 GB | 6.5 GB | Fits | Get file → | |
| Q5_K_S | 5.6 GB | 7.2 GB | Fits | Get file → | |
| Q5_K_M | 5.7 GB | 7.3 GB | Tight | Get file → | |
| Q6_K | 6.6 GB | 8.2 GB | Too big | Get file → | |
| Q8_0 | 8.5 GB | 10.1 GB | Too big | Get file → | |
| F16 | 16.1 GB | 17.6 GB | Too big | Get file → |
For 8 GB VRAM use IQ4_XS (file size 4.48 GB, memory 6.1 GB) or Q4_K_S (4.69 GB, 6.3 GB). For 12 GB VRAM use Q5_K_S (5.6 GB, 7.2 GB) or Q5_K_M (5.73 GB, 7.3 GB). Higher precision quants like Q8_0 require 10 GB+ VRAM.
What GPU do you need for Llama 3 ELYZA JP 8B Heretic?
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: the best quant that fits is Q3_K_L (4.3 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).
Which Llama 3 ELYZA JP 8B Heretic quant should you choose?
Q4_K_M is the usual starting point for Llama 3 ELYZA JP 8B Heretic: it balances file size and quality well. Here it is a 4.9 GB file.
The Q8_0 file is 8.5 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 IQ3_XS at 3.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Llama 3 ELYZA JP 8B Heretic
How much VRAM does Llama 3 ELYZA JP 8B Heretic need?
About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 Llama 3 ELYZA JP 8B Heretic on an 8 GB GPU?
Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Llama 3 ELYZA JP 8B Heretic GGUF?
It depends on the quant: IQ3_XS is 3.5 GB, Q3_K_S is 3.7 GB, IQ3_M is 3.8 GB, Q3_K_M is 4.0 GB, Q3_K_L is 4.3 GB, IQ4_XS is 4.5 GB and 8 more.
What context length does Llama 3 ELYZA JP 8B Heretic support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.
Where can I download Llama 3 ELYZA JP 8B Heretic GGUF?
The files are on Hugging Face in the ChiKoi7/Llama-3-ELYZA-JP-8B-Heretic-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 Llama 3 ELYZA JP 8B Heretic use?
Hugging Face lists the license as llama3. 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 IQ4_XS or Q4_K_S quantizations, which require about 6 GB of VRAM at 8k context.
Does this model support vision?
No, the model has no vision capabilities.
What license applies to this model?
The model is licensed under llama3, which allows non‑commercial use with attribution.