Salamandra 7b Instruct needs about 6.4 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 22 quants, from 3.3 GB (Q2_K) to 8.3 GB (Q8_0).
Salamandra 7b Instruct – a multilingual instruction‑tuned Llama model
Salamandra 7b Instruct is a 7.77 billion‑parameter Llama‑based decoder model. It was trained from scratch on 12.875 trillion tokens in 35 European languages and code. The model is instruction‑tuned and released under Apache 2.0.
Good at
- Multilingual text generation
- Instruction following
- Code‑aware responses
Limits
- No vision support
- Not aligned to avoid sensitive content
- Requires 8 k context for estimates
Best for
- Chat assistants
- Content drafting
- Code explanation
Who it’s for. Researchers and developers needing a multilingual Llama model for general‑purpose text generation. The model can be used in research or commercial applications, provided users are aware of its alignment limitations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.3 GB | 4.9 GB | Fits | Get file → | |
| IQ3_XS | 3.6 GB | 5.2 GB | Fits | Get file → | |
| Q3_K_S | 3.8 GB | 5.3 GB | Fits | Get file → | |
| IQ3_S | 3.8 GB | 5.3 GB | Fits | Get file → | |
| IQ3_M | 3.9 GB | 5.4 GB | Fits | Get file → | |
| Q3_K | 4.0 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_M | 4.0 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_L | 4.3 GB | 5.9 GB | Fits | Get file → | |
| IQ4_XS | 4.5 GB | 6.1 GB | Fits | Get file → | |
| Q4_0 | 4.6 GB | 6.2 GB | Fits | Get file → | |
| Q4_K_S | 4.7 GB | 6.2 GB | Fits | Get file → | |
| IQ4_NL | 4.7 GB | 6.3 GB | Fits | Get file → | |
| Q4_K | 4.9 GB | 6.4 GB | Fits | Get file → | |
| Q4_K_M | 4.9 GB | 6.4 GB | Fits | Get file → | |
| Q4_1 | 5.1 GB | 6.6 GB | Fits | Get file → | |
| Q5_0 | 5.5 GB | 7.1 GB | Fits | Get file → | |
| Q5_K_S | 5.5 GB | 7.1 GB | Fits | Get file → | |
| Q5_K | 5.6 GB | 7.2 GB | Fits | Get file → | |
| Q5_K_M | 5.6 GB | 7.2 GB | Fits | Get file → | |
| Q5_1 | 5.9 GB | 7.5 GB | Tight | Get file → | |
| Q6_K | 6.4 GB | 8.0 GB | Tight | Get file → | |
| Q8_0 | 8.3 GB | 9.8 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (4.65 GB file, ~6.2 GB memory). For 12 GB VRAM, Q4_K_M (4.85 GB file, ~6.4 GB memory). For 16 GB VRAM, Q5_K (5.59 GB file, ~7.2 GB memory). Estimates are approximate.
What GPU do you need for Salamandra 7b Instruct?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q3_K_L (4.3 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.4 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.3 GB file, about 9.8 GB in use).
Which Salamandra 7b Instruct quant should you choose?
Q4_K_M is the usual starting point for Salamandra 7b Instruct: it balances file size and quality well. Here it is a 4.9 GB file.
The Q8_0 file is 8.3 GB, about 1.7 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 3.3 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 7b Instruct
How much VRAM does Salamandra 7b Instruct need?
About 6.4 GB at Q4_K_M with an 8K context window. That is the 4.9 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 7b Instruct on an 8 GB GPU?
Yes, with Q6_K: the 6.4 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Salamandra 7b Instruct GGUF?
It depends on the quant: Q2_K is 3.3 GB, IQ3_XS is 3.6 GB, Q3_K_S is 3.8 GB, IQ3_S is 3.8 GB, IQ3_M is 3.9 GB, Q3_K is 4.0 GB and 16 more.
What context length does Salamandra 7b Instruct support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.
Where can I download Salamandra 7b Instruct GGUF?
The files are on Hugging Face in the RichardErkhov/BSC-LT_-_salamandra-7b-instruct-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 7b Instruct 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 7b Instruct on 8 GB VRAM?
Yes, using the Q4_0 quantization which requires about 6.2 GB of VRAM at 8 k context.
Does this model support image inputs?
No, it is a text‑only model with no vision capabilities.
Is the model aligned to avoid harmful content?
No, it has not been aligned via RLHF and may generate inappropriate content.