Marco Mini Instruct needs about 11.9 GB of memory at Q4_K_M (a 10.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.1 GB to 14.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
17.3B‑parameter Mixture‑of‑Experts instruction model
Marco‑Mini‑Instruct is a 17.3B‑parameter decoder‑only Transformer with sparse MoE layers. It activates only 0.86B parameters per token and is tuned for instruction following across many languages.
Good at
- Instruction following
- Multilingual reasoning
- Sparse‑MoE efficiency
Limits
- Requires 8‑k context for estimates
- No vision support
- Apache‑2.0 license
Best for
- Chat assistants
- Code generation prompts
- Multilingual Q&A
Who it’s for. Developers needing a lightweight instruction model that still offers strong multilingual performance. The model is suitable for applications where GPU memory is limited but high quality responses are required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.5 GB | Fits | Get file → | |
| IQ1_S | 3.6 GB | 5.0 GB | Fits | Get file → | |
| IQ1_M | 4.0 GB | 5.4 GB | Fits | Get file → | |
| IQ2_XXS | 4.6 GB | 6.0 GB | Fits | Get file → | |
| IQ2_XS | 5.1 GB | 6.6 GB | Fits | Get file → | |
| IQ2_S | 5.2 GB | 6.6 GB | Fits | Get file → | |
| IQ2_M | 5.7 GB | 7.1 GB | Fits | Get file → | |
| Q2_K_S | 5.9 GB | 7.4 GB | Tight | Get file → | |
| Q2_K | 6.4 GB | 7.8 GB | Tight | Get file → | |
| IQ3_XXS | 6.7 GB | 8.1 GB | Too big | Get file → | |
| IQ3_XS | 7.1 GB | 8.5 GB | Too big | Get file → | |
| IQ3_S | 7.5 GB | 8.9 GB | Too big | Get file → | |
| Q3_K_S | 7.5 GB | 8.9 GB | Too big | Get file → | |
| IQ3_M | 7.6 GB | 9.0 GB | Too big | Get file → | |
| Q3_K_M | 8.3 GB | 9.7 GB | Too big | Get file → | |
| Q3_K_L | 9.0 GB | 10.4 GB | Too big | Get file → | |
| IQ4_XS | 9.2 GB | 10.7 GB | Too big | Get file → | |
| IQ4_NL | 9.8 GB | 11.2 GB | Too big | Get file → | |
| Q4_0 | 9.8 GB | 11.3 GB | Too big | Get file → | |
| Q4_K_S | 9.9 GB | 11.3 GB | Too big | Get file → | |
| Q4_K_M | 10.5 GB | 11.9 GB | Too big | Get file → | |
| Q4_1 | 10.8 GB | 12.3 GB | Too big | Get file → | |
| Q5_K_S | 11.9 GB | 13.4 GB | Too big | Get file → | |
| Q5_K_M | 12.3 GB | 13.7 GB | Too big | Get file → | |
| Q6_K | 14.2 GB | 15.6 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (3.57 GB, 5 GB memory) or IQ1_M (3.96 GB, 5.4 GB memory). For 12‑GB VRAM, Q4_K_M (10.51 GB, 11.9 GB memory) or Q4_1 (10.84 GB, 12.3 GB memory) are suitable. Larger VRAM allows Q5_K_M (12.29 GB, 13.7 GB memory).
What GPU do you need for Marco Mini 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 IQ2_XXS (4.6 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q2_K (6.4 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_K_M (10.5 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (14.2 GB file, about 15.6 GB in use).
Which Marco Mini Instruct quant should you choose?
Q4_K_M is the usual starting point for Marco Mini Instruct: it balances file size and quality well. Here it is a 10.5 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 Mini Instruct
How much VRAM does Marco Mini Instruct need?
About 11.9 GB at Q4_K_M with an 8K context window. That is the 10.5 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 Marco Mini Instruct on an 8 GB GPU?
Yes, with Q2_K: the 6.4 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Marco Mini Instruct GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 3.6 GB, IQ1_M is 4.0 GB, IQ2_XXS is 4.6 GB, IQ2_XS is 5.1 GB, IQ2_S is 5.2 GB and 19 more.
What context length does Marco Mini 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 Mini Instruct GGUF?
The files are on Hugging Face in the mradermacher/Marco-Mini-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 Mini 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‑Mini‑Instruct on 8 GB VRAM?
Yes, using IQ1_S or IQ1_M quantizations will fit within 8 GB VRAM with approximate 5 GB memory usage.
Does the model support vision tasks?
No, the model is purely text‑based and does not include vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.