EuroLLM 9B Instruct Heretic needs about 7.5 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 7.5 GB (Q6_K).
EuroLLM 9B Instruct Heretic – multilingual instruction model
EuroLLM 9B Instruct Heretic is a 9.15B parameter model trained on 4 trillion tokens across 35 European languages and additional languages such as Arabic, Chinese, Hindi, Japanese, Korean, and Russian. It supports instruction following and machine translation with a 4,096 token context length.
Good at
- Multilingual instruction following
- Machine translation
- Reduced refusal behavior
Limits
- Context length only 4,096 tokens
- Requires a GPU for fast inference
- No vision support
Best for
- Building multilingual assistants
- Translating documents between EU languages
- Compliance work on a single 16 GB GPU
Who it’s for. Developers and researchers needing a robust multilingual LLM for European languages, or for Arabic, Chinese, Hindi, Japanese, Korean, and Russian. Suitable for projects requiring instruction following and translation without heavy reliance on English intermediaries.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.2 GB | Fits | Get file → | |
| IQ1_S | 2.3 GB | 3.5 GB | Fits | Get file → | |
| IQ1_M | 2.4 GB | 3.6 GB | Fits | Get file → | |
| IQ2_XXS | 2.7 GB | 3.9 GB | Fits | Get file → | |
| IQ2_XS | 2.9 GB | 4.1 GB | Fits | Get file → | |
| IQ2_S | 3.1 GB | 4.3 GB | Fits | Get file → | |
| IQ2_M | 3.3 GB | 4.5 GB | Fits | Get file → | |
| Q2_K_S | 3.4 GB | 4.6 GB | Fits | Get file → | |
| Q2_K | 3.6 GB | 4.8 GB | Fits | Get file → | |
| IQ3_XXS | 3.7 GB | 4.9 GB | Fits | Get file → | |
| IQ3_XS | 4.0 GB | 5.2 GB | Fits | Get file → | |
| Q3_K_S | 4.1 GB | 5.3 GB | Fits | Get file → | |
| IQ3_S | 4.2 GB | 5.4 GB | Fits | Get file → | |
| IQ3_M | 4.3 GB | 5.5 GB | Fits | Get file → | |
| Q3_K_M | 4.6 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_L | 4.9 GB | 6.1 GB | Fits | Get file → | |
| IQ4_XS | 5.0 GB | 6.3 GB | Fits | Get file → | |
| Q4_0 | 5.3 GB | 6.5 GB | Fits | Get file → | |
| IQ4_NL | 5.3 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_S | 5.3 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 5.6 GB | 6.8 GB | Fits | Get file → | |
| Q4_1 | 5.8 GB | 7.0 GB | Fits | Get file → | |
| Q5_K_S | 6.4 GB | 7.6 GB | Tight | Get file → | |
| Q5_K_M | 6.5 GB | 7.7 GB | Tight | Get file → | |
| Q6_K | 7.5 GB | 8.7 GB | Too big | Get file → |
For 8 GB VRAM use IQ1_S (2.26 GB) or IQ1_M (2.43 GB). For 12 GB VRAM use Q2_K (3.59 GB) or Q3_K_S (4.14 GB). For 16 GB VRAM use Q4_K_M (5.58 GB) or Q5_K_S (6.37 GB). Memory estimates are approximate.
What GPU do you need for EuroLLM 9B Instruct 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: the best quant that fits is the main file (0.0 GB file, about 1.9 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_XS (4.0 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_1 (5.8 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (7.5 GB file, about 9.4 GB in use).
Which EuroLLM 9B Instruct Heretic quant should you choose?
Q4_K_M is the usual starting point for EuroLLM 9B Instruct Heretic: it balances file size and quality well. Here it is a 5.6 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about EuroLLM 9B Instruct Heretic
How much VRAM does EuroLLM 9B Instruct Heretic need?
About 7.5 GB at Q4_K_M with an 8K context window. That is the 5.6 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 EuroLLM 9B Instruct Heretic on an 8 GB GPU?
Yes, with Q4_1: the 5.8 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of EuroLLM 9B Instruct Heretic GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 2.3 GB, IQ1_M is 2.4 GB, IQ2_XXS is 2.7 GB, IQ2_XS is 2.9 GB, IQ2_S is 3.1 GB and 19 more.
What context length does EuroLLM 9B Instruct Heretic support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.4 GB at 8K and 0.7 GB at 4K.
Where can I download EuroLLM 9B Instruct Heretic GGUF?
The files are on Hugging Face in the mradermacher/EuroLLM-9B-Instruct-heretic-i1-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 EuroLLM 9B Instruct Heretic 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, use the IQ1_S or IQ1_M quantized files which fit within 8 GB VRAM with an estimated 4.2–4.3 GB memory usage at 8k context.
Does this model support vision tasks?
No, it is a text-only model with no vision capabilities.
What is the maximum context length?
The model’s context length is limited to 4,096 tokens.