Leaderboard / Barcelona Supercomputing Center (ALIA)
Salamandra 7B Instruct
Barcelona Supercomputing Center (ALIA) · Salamandra · released 2026-06-30 · data checked 2026-11-03
Salamandra 7B Instruct is a 7.8B-parameter dense model from Barcelona Supercomputing Center (ALIA) (Europe), released 2026-06-30 under the Apache-2.0 license. It doesn't have enough reported benchmarks for an index score yet. It needs about 6.4 GB of memory at 4-bit with an 8K-token context.
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: Salamandra 7B 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. Measured by another lab. Source: huggingface.co, arxiv.org.
Specifications
- Lab
- Barcelona Supercomputing Center (ALIA) (ES · Europe)
- Architecture
- Dense transformer
- Total parameters
- 7.8B
- Active parameters
- All (dense)
- Size class
- Small
- Context window
- 164K tokens
- Input modalities
- text
- Reasoning
- Instruct (no thinking)
- License
- Apache-2.0
- Openness
- Open weights
- Memory to run
- ~6.4 GB at 4-bit, 8K context (more sizes)
- Hugging Face
- 9K downloads (30 days) · 3 likes
Compare with
- Salamandra 7B Instruct vs MiMo-7B-RL (7.8B, index 40.7)
- Salamandra 7B Instruct vs Gemma 3n E4B (7.8B, index 18.2)
- Salamandra 7B Instruct vs Ling 3.0 Tiny (7.9B, index 51.9)
Sources
Something wrong here? Report it.
Run it locally
No GGUF build from a well-known publisher yet.
vllm serve BSC-LT/salamandra-7b-instruct-2606Memory needed: weights, context cache and runtime buffers.
| Quantization | 4K context | 32K context | 164K context |
|---|---|---|---|
| 16-bit F16 | 17 GB | 20 GB | 38 GB |
| 8-bit Q8_0 | 9.4 GB | 13 GB | 30 GB |
| 4-bit Q4_K_M | 5.9 GB | 9.7 GB | 27 GB |