SA

Salamandra 2b Instruct

SalamandraGGUF by mradermacherUpdated 2025-02-13
Download on Hugging Face
Parameters2.25B
Context8K
Layers24
Architecturellama
Smallest quant1.1 GB
Quick answer

Salamandra 2b Instruct 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 12 quants, from 1.1 GB (Q2_K) to 4.5 GB (F16).

Salamandra 2b Instruct – 2.25B parameter instruction‑tuned Llama model

Salamandra 2b Instruct is a 2.25B parameter decoder‑only Llama model trained on 12.875 trillion tokens. It supports 8192 context tokens and is optimized for instruction following. The model is released under Apache‑2.0.

Good at

  • Coding assistance
  • Multilingual text generation
  • Instruction following

Limits

  • No vision support
  • Requires 8192 context tokens
  • Not aligned for sensitive content

Best for

  • Chatbots with limited GPU memory
  • Code generation in small projects
  • Research on instruction tuning

Who it’s for. Developers and researchers who need a lightweight instruction‑tuned Llama model for multilingual text or code tasks. The model is suitable for both academic and commercial use under the Apache‑2.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.1 GB 3.2 GB
Fits Get file →
Q3_K_S1.2 GB 3.3 GB
Fits Get file →
Q3_K_M1.3 GB 3.4 GB
Fits Get file →
Q3_K_L1.3 GB 3.4 GB
Fits Get file →
IQ4_XS1.4 GB 3.5 GB
Fits Get file →
Q4_K_S1.4 GB 3.6 GB
Fits Get file →
Q4_K_M1.5 GB 3.6 GB
Fits Get file →
Q5_K_S1.6 GB 3.8 GB
Fits Get file →
Q5_K_M1.7 GB 3.8 GB
Fits Get file →
Q6_K1.9 GB 4.0 GB
Fits Get file →
Q8_02.4 GB 4.5 GB
Fits Get file →
F164.5 GB 6.6 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.51 GB file, ~3.6 GB memory). For 12 GB VRAM, Q5_K_M (1.69 GB file, ~3.8 GB memory) is a good balance. For 24 GB VRAM, Q8_0 (2.4 GB file, ~4.5 GB memory) provides higher precision.

What GPU do you need for Salamandra 2b 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: 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).
  • 8 GB VRAM: the best quant that fits is F16 (4.5 GB file, about 6.6 GB in use).

Which Salamandra 2b Instruct quant should you choose?

Q4_K_M is the usual starting point for Salamandra 2b Instruct: 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

Architecturellama
Parameters2.25B
Layers24
Trained context8,192 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)1,013
Last updated2025-02-13

Frequently asked questions about Salamandra 2b Instruct

How much VRAM does Salamandra 2b Instruct 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 Instruct on an 8 GB GPU?

Yes, with F16: the 4.5 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Salamandra 2b Instruct GGUF?

It depends on the quant: Q2_K is 1.1 GB, Q3_K_S is 1.2 GB, Q3_K_M is 1.3 GB, Q3_K_L is 1.3 GB, IQ4_XS is 1.4 GB, Q4_K_S is 1.4 GB and 6 more.

What context length does Salamandra 2b 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 1.6 GB at 8K and 1.6 GB at 8K.

Where can I download Salamandra 2b Instruct GGUF?

The files are on Hugging Face in the mradermacher/salamandra-2b-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 2b 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 2b Instruct on 8 GB VRAM?

Yes, using Q4_K_M or Q4_K_S quantizations will fit within 8 GB VRAM with approximate memory usage of 3.6 GB at 8192 context.

Does this model support image inputs?

No, Salamandra 2b Instruct is a text‑only model with no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing both research and commercial use.

Other GGUFs of salamandra-2b-instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Salamandra models

All Salamandra →

Other tiny models

All tiny models →