EU

EuroLLM 9B Instruct 2512

EurollmGGUF by mradermacherUpdated 2026-02-06
Download on Hugging Face
Parameters9.15B
Context32K
Layers42
Architecturellama
Smallest quant0.0 GB
Quick answer

EuroLLM 9B Instruct 2512 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). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

EuroLLM 9B Instruct 2512 – 9.15B multilingual LLM with 32k context

EuroLLM 9B Instruct 2512 is a 9.15B parameter transformer trained on 32,768 token context. It supports a wide range of European languages and is released under Apache‑2.0. The model is available in multiple GGUF quantizations.

Good at

  • Multilingual text generation
  • Long‑context handling
  • Instruction following

Limits

  • No vision support
  • Not aligned to human preferences
  • Requires 8k context for memory estimates

Best for

  • Chatbots in European languages
  • Content drafting with long context
  • Educational tutoring

Who it’s for. Developers and researchers needing a multilingual LLM with extended context. The model is suitable for applications that can tolerate unaligned outputs and require a large token window.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.9 GB
Fits Get file →
IQ1_S2.3 GB 4.2 GB
Fits Get file →
IQ1_M2.4 GB 4.3 GB
Fits Get file →
IQ2_XXS2.7 GB 4.6 GB
Fits Get file →
IQ2_XS2.9 GB 4.8 GB
Fits Get file →
IQ2_S3.1 GB 5.0 GB
Fits Get file →
IQ2_M3.3 GB 5.2 GB
Fits Get file →
Q2_K_S3.4 GB 5.3 GB
Fits Get file →
Q2_K3.6 GB 5.5 GB
Fits Get file →
IQ3_XXS3.7 GB 5.6 GB
Fits Get file →
IQ3_XS4.0 GB 5.9 GB
Fits Get file →
Q3_K_S4.1 GB 6.1 GB
Fits Get file →
IQ3_S4.2 GB 6.1 GB
Fits Get file →
IQ3_M4.3 GB 6.2 GB
Fits Get file →
Q3_K_M4.6 GB 6.5 GB
Fits Get file →
Q3_K_L4.9 GB 6.8 GB
Fits Get file →
IQ4_XS5.0 GB 7.0 GB
Fits Get file →
Q4_05.3 GB 7.2 GB
Tight Get file →
IQ4_NL5.3 GB 7.2 GB
Tight Get file →
Q4_K_S5.3 GB 7.2 GB
Tight Get file →
Q4_K_M5.6 GB 7.5 GB
Tight Get file →
Q4_15.8 GB 7.7 GB
Tight Get file →
Q5_K_S6.4 GB 8.3 GB
Too big Get file →
Q5_K_M6.5 GB 8.4 GB
Too big Get file →
Q6_K7.5 GB 9.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (4.2 GB) or IQ1_M (4.3 GB). For 12 GB VRAM, IQ2_S (5 GB) or Q2_K (5.5 GB) are good choices. For 16 GB VRAM, Q3_K_M (6.5 GB) or Q4_K_M (7.5 GB) provide higher quality while staying within memory limits.

What GPU do you need for EuroLLM 9B Instruct 2512?

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 2512 quant should you choose?

Q4_K_M is the usual starting point for EuroLLM 9B Instruct 2512: 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

Architecturellama
Parameters9.15B
Layers42
Trained context32,768 tokens
KV cache (fp16)168 KB per token

Source

Quantized bymradermacher
FamilyEurollm
Licenseapache-2.0
Downloads (HF)1,109
Last updated2026-02-06

Frequently asked questions about EuroLLM 9B Instruct 2512

How much VRAM does EuroLLM 9B Instruct 2512 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 2512 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 2512 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 2512 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download EuroLLM 9B Instruct 2512 GGUF?

The files are on Hugging Face in the mradermacher/EuroLLM-9B-Instruct-2512-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 2512 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 EuroLLM 9B Instruct 2512 on 8 GB VRAM?

Yes, using the IQ1_S or IQ1_M quantization, which estimate 4.2–4.3 GB memory at 8k context.

Does the model support vision tasks?

No, EuroLLM 9B Instruct 2512 is a text‑only model.

What license applies to this model?

The model is released under Apache License 2.0.

Other GGUFs of EuroLLM-9B-Instruct-2512

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Eurollm models

All Eurollm →

Other small models

All small models →