BestLLMfor EN Your hardware. Your LLM. Your call.
APIOpen data Find my LLM
Model fiche

Salamandra 40B Instruct

By BSC · Spain

chat general multilingual fr
Parameters
40B
License
Apache 2.0
Context
8k
VRAM (Q4)
24 GB
Released
December 2024

Overview

BSC's 40B scaled-up Salamandra covering 35 EU languages with native Catalan support — though the HuggingFace repo is gated and successor ALIA-40B is now available.

When to pick this model

  • EU-sovereign workloads needing 40B-class quality
  • Romance-language content generation, especially Catalan
  • Public-sector and regulated deployments in Europe
  • Multilingual research baselines across 35 EU languages
  • Workflows already provisioned for ALIA-40B comparisons

VRAM requirements by quantization

QuantizationVRAM required
Q4_K_M (recommended)24 GB
Q5_K_M29 GB
Q8_043 GB
FP16 (no quantization)80 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

Strengths

  • Sovereign European model purpose-built for Romance languages
  • Unique native Catalan capability among open models
  • Apache 2.0 license
  • 7.68T tokens with strong Iberian-language coverage

Limitations

  • ~24 GB VRAM at Q4
  • 8192-token context limits modern long-context use
  • Limited fine-tune ecosystem and gated repo access

Architecture & training

Architecture: Dense · 40B · BSC MareNostrum · sovereign Romance languages

Training: Barcelona Supercomputing Center — 7.68T tokens, strong in Catalan, Spanish, French, Occitan.

Verdict

The strongest open model for Catalan and Iberian Romance languages — but check ALIA-40B first if you can run either.

Quick start

ollama pull hf.co/BSC-LT/salamandra-40b-instruct-GGUF

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.

Tools

Is Salamandra 40B Instruct the right pick for you?

Compute self-hosted ROI → Back to catalog