Salamandra 7B Instruct — Hardware Requirements & GPU Compatibility
Chat
Salamandra 7B Instruct is a 7.8-billion-parameter multilingual model developed by the Barcelona Supercomputing Center (BSC-LT) as part of a European initiative to build high-quality open language models. It has particular strength in Iberian languages including Spanish, Catalan, Portuguese, and Basque, while also supporting English and other major European languages. This model is an excellent choice for users who need strong performance in Spanish or other Iberian languages that are often underserved by mainstream LLMs. Running it locally ensures data privacy for sensitive multilingual workflows, and at 7B parameters it fits comfortably on a single consumer GPU with 8 GB or more of VRAM.
70.3K downloads
76 likesSpecifications
- Publisher
- BSC-LT
- Parameters
- 7.8B
- Architecture
- LlamaForCausalLM
- Context Length
- 8,192 tokens
- Vocabulary Size
- 256,000
- Release Date
- 2025-10-22
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does Salamandra 7B Instruct Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 16.1 GB | 16.9 GB | 15.54 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Salamandra 7B Instruct?
BF16 · 16.1 GBSalamandra 7B Instruct (BF16) requires 16.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 21+ GB is recommended. Using the full 8K context window can add up to 0.8 GB, bringing total usage to 16.9 GB. 6 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroom
Which Devices Can Run Salamandra 7B Instruct?
BF16 · 16.1 GB21 devices with unified memory can run Salamandra 7B Instruct, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).
Runs great
— Plenty of headroomRelated Models
Derivatives (3)
Frequently Asked Questions
- How much VRAM does Salamandra 7B Instruct need?
Salamandra 7B Instruct requires 16.1 GB of VRAM at BF16. Full 8K context adds up to 0.8 GB (16.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 7.8B × 16 bits ÷ 8 = 15.5 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 1.4 GB (at full 8K context)
VRAM usage by quantization
BF1616.1 GBBF16 + full context16.9 GB- Can I run Salamandra 7B Instruct on a Mac?
Salamandra 7B Instruct requires at least 16.1 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Salamandra 7B Instruct locally?
Yes — Salamandra 7B Instruct can run locally on consumer hardware. At BF16 quantization it needs 16.1 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Salamandra 7B Instruct?
At BF16, Salamandra 7B Instruct can reach ~181 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~41 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 16.1 × 0.55 = ~181 tok/s
Estimated speed at BF16 (16.1 GB)
AMD Instinct MI300X~181 tok/sNVIDIA GeForce RTX 4090~41 tok/sNVIDIA H100 SXM~135 tok/sAMD Instinct MI250X~112 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Salamandra 7B Instruct?
At BF16, the download is about 15.54 GB.