Salamandra 2B Instruct — Hardware Requirements & GPU Compatibility
Chat
Salamandra 2B Instruct is a 2.3B-parameter open language model from BSC-LT. It supports a context window of up to 8,192 tokens. At BF16 it needs about 5.21 GB of VRAM — see which GPUs and Macs can run it below.
6.3K downloads
27 likesSpecifications
- Publisher
- BSC-LT
- Parameters
- 2.3B
- 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 2B Instruct Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16 | 16.00 | 5.2 GB | 6.4 GB | 4.51 GB | Brain floating point 16 — preferred for training |
Which GPUs Can Run Salamandra 2B Instruct?
BF16 · 5.2 GBSalamandra 2B Instruct (BF16) requires 5.2 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 7+ GB is recommended. Using the full 8K context window can add up to 1.2 GB, bringing total usage to 6.4 GB. 35 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Salamandra 2B Instruct?
BF16 · 5.2 GB33 devices with unified memory can run Salamandra 2B Instruct, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomRelated Models
Frequently Asked Questions
- How much VRAM does Salamandra 2B Instruct need?
Salamandra 2B Instruct requires 5.2 GB of VRAM at BF16. Full 8K context adds up to 1.2 GB (6.4 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 2.3B × 16 bits ÷ 8 = 4.5 GB
KV Cache + Overhead ≈ 0.7 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 1.9 GB (at full 8K context)
VRAM usage by quantization
BF165.2 GBBF16 + full context6.4 GB- Can I run Salamandra 2B Instruct on a Mac?
Salamandra 2B Instruct requires at least 5.2 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 2B Instruct locally?
Yes — Salamandra 2B Instruct can run locally on consumer hardware. At BF16 quantization it needs 5.2 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Salamandra 2B Instruct?
At BF16, Salamandra 2B Instruct can reach ~560 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~126 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 ÷ 5.2 × 0.55 = ~560 tok/s
Estimated speed at BF16 (5.2 GB)
~560 tok/s~126 tok/s~418 tok/s~346 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Salamandra 2B Instruct?
At BF16, the download is about 4.51 GB.
- Which GPUs can run Salamandra 2B Instruct?
35 consumer GPUs can run Salamandra 2B Instruct at BF16 (5.2 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 35 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Salamandra 2B Instruct?
33 devices with unified memory can run Salamandra 2B Instruct at BF16 (5.2 GB), including Mac Mini M4 (16 GB), Mac Mini M4 (32 GB), Mac Mini M4 Pro (24 GB), Mac Mini M4 Pro (48 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.