Marco Nano Instruct needs about 6.8 GB of memory at Q4_K_M (a 5.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.1 GB to 7.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Marco Nano Instruct – a sparse Mixture‑of‑Experts instruct model
Marco Nano Instruct is a post‑trained variant of Marco‑Nano‑Base. It uses a decoder‑only Transformer with sparse MoE layers and activates only 0.6B of its 8B parameters per token. The model supports a 32,768‑token context window.
Good at
- Reasoning
- Multilingual instruction following
- Sparse parameter efficiency
Limits
- Requires large VRAM for higher‑quality quants
- No vision support
- Apache‑2.0 license
Best for
- Chatting in multiple languages
- Answering complex reasoning questions
- Fine‑tuning on small datasets
Who it’s for. Developers and researchers who need a lightweight instruct model with strong multilingual and reasoning capabilities. The model is suitable for local deployment on GPUs with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.5 GB | Fits | Get file → | |
| IQ1_S | 2.6 GB | 4.1 GB | Fits | Get file → | |
| IQ1_M | 2.7 GB | 4.2 GB | Fits | Get file → | |
| IQ2_XXS | 2.9 GB | 4.4 GB | Fits | Get file → | |
| IQ2_XS | 3.1 GB | 4.6 GB | Fits | Get file → | |
| IQ2_S | 3.1 GB | 4.6 GB | Fits | Get file → | |
| IQ2_M | 3.3 GB | 4.7 GB | Fits | Get file → | |
| Q2_K | 3.3 GB | 4.8 GB | Fits | Get file → | |
| Q2_K_S | 3.4 GB | 4.8 GB | Fits | Get file → | |
| IQ3_XXS | 3.6 GB | 5.0 GB | Fits | Get file → | |
| IQ3_XS | 3.7 GB | 5.1 GB | Fits | Get file → | |
| IQ3_S | 3.9 GB | 5.3 GB | Fits | Get file → | |
| Q3_K_S | 3.9 GB | 5.3 GB | Fits | Get file → | |
| IQ3_M | 3.9 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_M | 4.2 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_L | 4.4 GB | 5.8 GB | Fits | Get file → | |
| IQ4_XS | 4.4 GB | 5.8 GB | Fits | Get file → | |
| IQ4_NL | 4.6 GB | 6.0 GB | Fits | Get file → | |
| Q4_0 | 4.6 GB | 6.0 GB | Fits | Get file → | |
| Q4_K_S | 4.9 GB | 6.3 GB | Fits | Get file → | |
| Q4_1 | 5.1 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 5.4 GB | 6.8 GB | Fits | Get file → | |
| Q5_K_S | 5.7 GB | 7.1 GB | Fits | Get file → | |
| Q5_K_M | 6.1 GB | 7.6 GB | Tight | Get file → | |
| Q6_K | 7.2 GB | 8.6 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (file size 2.62 GB, estimated 4.1 GB memory). For 12‑GB VRAM, IQ2_M (3.28 GB, 4.7 GB memory) or Q3_K_M (4.21 GB, 5.6 GB memory). For 16‑GB VRAM, Q4_K_M (5.37 GB, 6.8 GB memory) or Q5_K_M (6.11 GB, 7.6 GB memory).
What GPU do you need for Marco Nano 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 the main file (0.1 GB file, about 1.5 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_0 (4.6 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (6.1 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (7.2 GB file, about 8.6 GB in use).
Which Marco Nano Instruct quant should you choose?
Q4_K_M is the usual starting point for Marco Nano Instruct: it balances file size and quality well. Here it is a 5.4 GB file.
If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Marco Nano Instruct
How much VRAM does Marco Nano Instruct need?
About 6.8 GB at Q4_K_M with an 8K context window. That is the 5.4 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 Marco Nano Instruct on an 8 GB GPU?
Yes, with Q5_K_M: the 6.1 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Marco Nano Instruct GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 2.6 GB, IQ1_M is 2.7 GB, IQ2_XXS is 2.9 GB, IQ2_XS is 3.1 GB, IQ2_S is 3.1 GB and 19 more.
What context length does Marco Nano Instruct support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download Marco Nano Instruct GGUF?
The files are on Hugging Face in the mradermacher/Marco-Nano-Instruct-i1-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 Marco Nano 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 Marco Nano Instruct on a GPU with 8 GB VRAM?
Yes, the IQ1_S quant uses 2.62 GB file size and needs about 4.1 GB VRAM at 8,192‑token context. It fits comfortably on 8 GB VRAM.
Does the model support image inputs?
No, Marco Nano Instruct is a text‑only model and does not provide vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use and modification.