Salamandra 7b Instruct 2606 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 12 quants, from 3.3 GB (Q2_K) to 15.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Salamandra 7b Instruct 2606 – a 7.77B parameter instruction‑tuned LLM
Salamandra 7b Instruct 2606 is a 7.77B llama‑based model trained on 9.83 trillion tokens. It is tuned for instruction following, multi‑turn dialogue, and robust input handling across many European languages.
Good at
- Instruction following
- Multi‑turn conversation
- Robustness to noisy input
Limits
- No vision support
- Requires at least 8k context for full performance
- Apache‑2.0 license
Best for
- Chatbot development
- Text summarization
- Translation tasks
Who it’s for. Developers building conversational agents or language tools that need reliable instruction compliance and multi‑turn context awareness. The model is suitable for applications requiring support for multiple European languages.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.3 GB | 4.9 GB | Fits | Get file → | |
| Q3_K_S | 3.8 GB | 5.3 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_K_S | 4.7 GB | 6.2 GB | Fits | Get file → | |
| Q4_K_M | 4.9 GB | 6.4 GB | Fits | Get file → | |
| Q5_K_S | 5.5 GB | 7.1 GB | Fits | Get file → | |
| Q5_K_M | 5.6 GB | 7.2 GB | Fits | 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 → | |
| F16 | 15.5 GB | 17.1 GB | Too big | Get file → |
For 8GB VRAM, Q4_K_M (4.85 GB file, ~6.4 GB memory at 8k context) is a good balance. With 12GB VRAM, Q5_K_M (5.59 GB file, ~7.2 GB memory) offers higher quality. For 16GB VRAM, Q6_K (6.38 GB file, ~8 GB memory) provides further improvement.
What GPU do you need for Salamandra 7b Instruct 2606?
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).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.3 GB file, about 9.8 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (15.5 GB file, about 17.1 GB in use).
Which Salamandra 7b Instruct 2606 quant should you choose?
Q4_K_M is the usual starting point for Salamandra 7b Instruct 2606: 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 2606
How much VRAM does Salamandra 7b Instruct 2606 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 2606 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 2606 GGUF?
It depends on the quant: Q2_K is 3.3 GB, Q3_K_S is 3.8 GB, Q3_K_M is 4.0 GB, Q3_K_L is 4.3 GB, IQ4_XS is 4.5 GB, Q4_K_S is 4.7 GB and 6 more.
What context length does Salamandra 7b Instruct 2606 support?
The GGUF header lists a trained context length of 163,840 tokens (160K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Salamandra 7b Instruct 2606 GGUF?
The files are on Hugging Face in the mradermacher/salamandra-7b-instruct-2606-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 2606 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 2606 on 8 GB VRAM?
Yes, the Q4_K_M quant requires about 6.4 GB memory at 8k context, which fits within 8 GB VRAM.
Does the model support vision tasks?
No, the model does not have vision capabilities.
What is the recommended temperature for sampling?
Use temperatures close to zero (0–0.2) and avoid repetition penalties for best results.