Leaderboard / EuroLLM (UTTER consortium)

EuroLLM 9B Instruct (2512)

Name: EuroLLM 9B Instruct (2512)
Author: EuroLLM (UTTER consortium)

EuroLLM (UTTER consortium) · EuroLLM · released 2026-01-26 · data checked 2026-11-03

EuroLLM 9B Instruct (2512) is a 9.2B-parameter dense model from EuroLLM (UTTER consortium) (Europe), released 2026-01-26 under the Apache-2.0 license. It doesn't have enough reported benchmarks for an index score yet. It needs about 7.6 GB of memory at 4-bit with an 8K-token context.

The published results tables are for the original EuroLLM-9B (2024), not this 2512 update, which adds long-context training and new post-training. They are shown as earlier-version scores.

Small LM Index

—

Needs 2 core benchmarks (has 0)

Parameters

9.2B

Dense

Price per 1M tokens

—

No hosted API on OpenRouter; self-host

Context window

32K

tokens

Benchmarks

Each bar shows this model's score. The tick marks the best small model on that benchmark.

No benchmark results for this release yet. Know of one? Send it.

Earlier version: EuroLLM 9B Instruct (2024) Earlier version

Published for the previous release, not this one. Shown for context only: they don't count toward the index or appear in tables. Source: huggingface.co, arxiv.org.

Multilingual MMLU · EU20-MMLU, average over EU official languages55.4

IFEval65.7

Specifications

Lab: EuroLLM (UTTER consortium) (PT · Europe)
Architecture: Dense transformer
Total parameters: 9.2B
Active parameters: All (dense)
Size class: Small
Context window: 32K tokens
Input modalities: text
Reasoning: Instruct (no thinking)
License: Apache-2.0
Openness: Fully open: weights, training data and code
Memory to run: ~7.6 GB at 4-bit, 8K context (more sizes)
Hugging Face: 11.6K downloads (30 days) · 16 likes

Weights on Hugging Face ↗

Compare with

EuroLLM 9B Instruct (2512) vs Qwen3.5 9B (9B, index 63.9)
EuroLLM 9B Instruct (2512) vs Nemotron Nano 9B v2 (8.9B, index 52.5)
EuroLLM 9B Instruct (2512) vs Apertus 1.5 8B (8.9B, index 20.1)

Sources

https://huggingface.co/utter-project/EuroLLM-9B-Instruct-2512

Something wrong here? Report it.

Run it locally

No GGUF build from a well-known publisher yet.

vLLM (GPU server)

vllm serve utter-project/EuroLLM-9B-Instruct-2512

Full-precision weights, for a server GPU.

Memory needed: weights, context cache and runtime buffers.

Quantization	4K context	32K context
16-bit F16	20 GB	24 GB
8-bit Q8_0	11 GB	16 GB
4-bit Q4_K_M	6.9 GB	12 GB

Check it against your GPU, Mac or phone →