Marco MT Algharb needs about 10.8 GB of memory at Q4_K_M (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 12.1 GB (Q6_K).
14.8B Qwen3 translation model in GGUF format
Marco MT Algharb is a 14.8B parameter Qwen3 model fine‑tuned for machine translation. It supports 13 language pairs and is released under Apache‑2.0. The model is available in multiple quantizations for efficient inference.
Good at
- High‑quality translation across 13 language pairs
- Large context support of 4096 tokens
- Flexible quantization options
Limits
- No vision support
- Requires 8k context for memory estimates
- License is Apache‑2.0
Best for
- Translation pipelines needing 8k context
- Low‑latency inference on GPUs with 8–12 GB VRAM
- Research on multilingual translation models
Who it’s for. Developers building translation services or research projects that need a large Qwen3‑based model. The model is suitable for users who can run GGUF files with llama.cpp or vllm.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.2 GB | Fits | Get file → | |
| IQ1_S | 3.6 GB | 4.8 GB | Fits | Get file → | |
| IQ1_M | 3.8 GB | 5.0 GB | Fits | Get file → | |
| IQ2_XXS | 4.3 GB | 5.5 GB | Fits | Get file → | |
| IQ2_XS | 4.7 GB | 5.9 GB | Fits | Get file → | |
| IQ2_S | 5.0 GB | 6.1 GB | Fits | Get file → | |
| IQ2_M | 5.3 GB | 6.5 GB | Fits | Get file → | |
| Q2_K_S | 5.4 GB | 6.6 GB | Fits | Get file → | |
| Q2_K | 5.8 GB | 6.9 GB | Fits | Get file → | |
| IQ3_XXS | 5.9 GB | 7.1 GB | Fits | Get file → | |
| IQ3_XS | 6.4 GB | 7.5 GB | Tight | Get file → | |
| Q3_K_S | 6.7 GB | 7.8 GB | Tight | Get file → | |
| IQ3_S | 6.7 GB | 7.9 GB | Tight | Get file → | |
| IQ3_M | 6.9 GB | 8.1 GB | Too big | Get file → | |
| Q3_K_M | 7.3 GB | 8.5 GB | Too big | Get file → | |
| Q3_K_L | 7.9 GB | 9.1 GB | Too big | Get file → | |
| IQ4_XS | 8.1 GB | 9.3 GB | Too big | Get file → | |
| IQ4_NL | 8.5 GB | 9.7 GB | Too big | Get file → | |
| Q4_0 | 8.5 GB | 9.7 GB | Too big | Get file → | |
| Q4_K_S | 8.6 GB | 9.7 GB | Too big | Get file → | |
| Q4_K_M | 9.0 GB | 10.2 GB | Too big | Get file → | |
| Q4_1 | 9.4 GB | 10.6 GB | Too big | Get file → | |
| Q5_K_S | 10.3 GB | 11.4 GB | Too big | Get file → | |
| Q5_K_M | 10.5 GB | 11.7 GB | Too big | Get file → | |
| Q6_K | 12.1 GB | 13.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 9 GB, 10.8 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (10.51 GB, 12.4 GB memory) or Q6_K (12.12 GB, 14 GB memory). Smaller quants such as IQ1_S or IQ2_XXS reduce file size but increase memory usage.
What GPU do you need for Marco MT Algharb?
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 (0.0 GB file, about 1.8 GB in use).
- 6 GB VRAM: the best quant that fits is IQ1_M (3.8 GB file, about 5.7 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_XXS (5.9 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_1 (9.4 GB file, about 11.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (12.1 GB file, about 14.0 GB in use).
Which Marco MT Algharb quant should you choose?
Q4_K_M is the usual starting point for Marco MT Algharb: it balances file size and quality well. Here it is a 9.0 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 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 MT Algharb
How much VRAM does Marco MT Algharb need?
About 10.8 GB at Q4_K_M with an 8K context window. That is the 9.0 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 MT Algharb on an 8 GB GPU?
Yes, with IQ3_XXS: the 5.9 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 MT Algharb GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 3.6 GB, IQ1_M is 3.8 GB, IQ2_XXS is 4.3 GB, IQ2_XS is 4.7 GB, IQ2_S is 5.0 GB and 19 more.
What context length does Marco MT Algharb support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.3 GB at 8K and 0.7 GB at 4K.
Where can I download Marco MT Algharb GGUF?
The files are on Hugging Face in the mradermacher/Marco-MT-Algharb-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 MT Algharb 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 this model on 8 GB VRAM?
Yes, using the Q4_K_M quant which requires about 10.8 GB memory at 8k context. It will fit on 8 GB VRAM with careful batching.
What license does the model use?
The model is licensed under Apache License Version 2.0.
Does the model support vision tasks?
No, the model does not have vision capabilities.