Salamandra 2b needs about 3.6 GB of memory at Q4_K_M (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 1.1 GB (Q2_K) to 2.4 GB (Q8_0).
Salamandra 2b – a 2.25B‑parameter multilingual LLM
Salamandra 2b is a 2.25B‑parameter model based on the llama architecture. It supports 8192 context tokens and is released under the Apache‑2.0 license. The model is available in multiple quantizations for different memory budgets.
Good at
- Multilingual text generation
- Instruction following
- Low‑memory inference
Limits
- No vision support
- Limited to 8192 tokens
- Requires at least 3.2 GB VRAM for Q2_K
Best for
- Chatbots on edge devices
- Rapid prototyping of multilingual apps
- Educational language tools
Who it’s for. Developers and researchers needing a compact, multilingual LLM that can run on modest hardware. The model is suitable for projects that require a balance between performance and resource usage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.1 GB | 3.2 GB | Fits | Get file → | |
| IQ3_XS | 1.2 GB | 3.3 GB | Fits | Get file → | |
| IQ3_S | 1.2 GB | 3.3 GB | Fits | Get file → | |
| Q3_K_S | 1.2 GB | 3.3 GB | Fits | Get file → | |
| IQ3_M | 1.2 GB | 3.4 GB | Fits | Get file → | |
| Q3_K | 1.3 GB | 3.4 GB | Fits | Get file → | |
| Q3_K_M | 1.3 GB | 3.4 GB | Fits | Get file → | |
| Q3_K_L | 1.3 GB | 3.4 GB | Fits | Get file → | |
| IQ4_XS | 1.4 GB | 3.5 GB | Fits | Get file → | |
| Q4_0 | 1.4 GB | 3.5 GB | Fits | Get file → | |
| IQ4_NL | 1.4 GB | 3.5 GB | Fits | Get file → | |
| Q4_K_S | 1.4 GB | 3.6 GB | Fits | Get file → | |
| Q4_K | 1.5 GB | 3.6 GB | Fits | Get file → | |
| Q4_K_M | 1.5 GB | 3.6 GB | Fits | Get file → | |
| Q4_1 | 1.5 GB | 3.6 GB | Fits | Get file → | |
| Q5_0 | 1.6 GB | 3.7 GB | Fits | Get file → | |
| Q5_K_S | 1.6 GB | 3.8 GB | Fits | Get file → | |
| Q5_K | 1.7 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_M | 1.7 GB | 3.8 GB | Fits | Get file → | |
| Q5_1 | 1.7 GB | 3.8 GB | Fits | Get file → | |
| Q6_K | 1.9 GB | 4.0 GB | Fits | Get file → | |
| Q8_0 | 2.4 GB | 4.5 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.51 GB file, ~3.6 GB VRAM). For 6 GB VRAM, Q3_K_M (1.28 GB file, ~3.4 GB VRAM). For 4 GB VRAM, Q2_K (1.09 GB file, ~3.2 GB VRAM).
What GPU do you need for Salamandra 2b?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q6_K (1.9 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (2.4 GB file, about 4.5 GB in use).
Which Salamandra 2b quant should you choose?
Q4_K_M is the usual starting point for Salamandra 2b: it balances file size and quality well. Here it is a 1.5 GB file.
The Q8_0 file is 2.4 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 1.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Salamandra 2b
How much VRAM does Salamandra 2b need?
About 3.6 GB at Q4_K_M with an 8K context window. That is the 1.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Salamandra 2b on an 8 GB GPU?
Yes, with Q8_0: the 2.4 GB file needs about 4.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Salamandra 2b GGUF?
It depends on the quant: Q2_K is 1.1 GB, IQ3_XS is 1.2 GB, IQ3_S is 1.2 GB, Q3_K_S is 1.2 GB, IQ3_M is 1.2 GB, Q3_K is 1.3 GB and 16 more.
What context length does Salamandra 2b support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.6 GB at 8K and 1.6 GB at 8K.
Where can I download Salamandra 2b GGUF?
The files are on Hugging Face in the RichardErkhov/BSC-LT_-_salamandra-2b-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Salamandra 2b use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Salamandra 2b on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 3.6 GB VRAM at 8192 context tokens, fitting within an 8 GB GPU.
Does Salamandra 2b support vision tasks?
No, the model is text‑only and does not include vision capabilities.