Moulsot.V0.3 needs about 2.5 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.8 GB (Q2_K) to 3.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Moulsot.V0.3 – 1.72B parameter Qwen3VL model with vision and ASR for Moroccan Darija
Moulsot.V0.3 is a 1.72B parameter Qwen3VL model trained on 65536 context tokens. It supports vision and automatic speech recognition for Moroccan Darija with code‑switching to French, English and Arabic. The model is released under apache-2.0.
Good at
- Vision‑enabled ASR for Darija
- Code‑switching support
- Multimodal inference
Limits
- No vision support beyond ASR
- Requires 8k context for memory estimates
- No specialized domain adaptation
Best for
- Transcribing Darija audio
- Voice assistants in Moroccan markets
- Media content indexing
Who it’s for. Developers building speech interfaces for Moroccan Darija. Researchers needing a vision‑enabled ASR model with code‑switching capability. Teams requiring a lightweight, open‑source model for local deployment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.8 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_S | 0.9 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_M | 0.9 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_L | 1.0 GB | 2.4 GB | Fits | Get file → | |
| IQ4_XS | 1.0 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_S | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q5_K_S | 1.2 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_M | 1.3 GB | 2.7 GB | Fits | Get file → | |
| Q6_K | 1.4 GB | 2.9 GB | Fits | Get file → | |
| Q8_0 | 1.8 GB | 3.3 GB | Fits | Get file → | |
| F16 | 3.4 GB | 4.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.11 GB, 2.5 GB memory) or Q5_K_S (1.23 GB, 2.7 GB memory). For 4 GB VRAM, Q2_K (0.78 GB, 2.2 GB memory) is the smallest option. Larger budgets can use Q8_0 (1.83 GB, 3.3 GB memory) or F16 (3.45 GB, 4.9 GB memory).
What GPU do you need for Moulsot.V0.3?
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 Q8_0 (1.8 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.4 GB file, about 4.9 GB in use).
Which Moulsot.V0.3 quant should you choose?
Q4_K_M is the usual starting point for Moulsot.V0.3: it balances file size and quality well. Here it is a 1.1 GB file.
The Q8_0 file is 1.8 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 0.8 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 Moulsot.V0.3
How much VRAM does Moulsot.V0.3 need?
About 2.5 GB at Q4_K_M with an 8K context window. That is the 1.1 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 Moulsot.V0.3 on an 8 GB GPU?
Yes, with F16: the 3.4 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Moulsot.V0.3 GGUF?
It depends on the quant: Q2_K is 0.8 GB, Q3_K_S is 0.9 GB, Q3_K_M is 0.9 GB, Q3_K_L is 1.0 GB, IQ4_XS is 1.0 GB, Q4_K_S is 1.1 GB and 6 more.
What context length does Moulsot.V0.3 support?
The GGUF header lists a trained context length of 65,536 tokens (64K). 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 Moulsot.V0.3 GGUF?
The files are on Hugging Face in the mradermacher/moulsot.v0.3-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 Moulsot.V0.3 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 Moulsot.V0.3 on 8 GB VRAM?
Yes, using Q4_K_M or Q5_K_S quantizations will fit within 8 GB VRAM with estimated memory usage of 2.5–2.7 GB at 8k context.
Does the model support other languages besides Darija?
The model is primarily trained for Moroccan Darija with code‑switching to French, English and Arabic. Other languages are not supported.
What license applies to Moulsot.V0.3?
The model is released under the apache-2.0 license.