YuLan Mini needs about 3.1 GB of memory at Q4_K_M (a 1.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 1.5 GB (Q3_K_S) to 9.7 GB (F32).
YuLan Mini – a 2.4B‑parameter language model focused on code and math
YuLan Mini is a lightweight 2.42B‑parameter model based on the Yulan family. It is pre‑trained on 1.08T tokens and excels in coding and mathematics. The model is released under the MIT license and is available in multiple GGUF quantizations.
Good at
- Coding tasks
- Mathematics problems
- Short context generation
Limits
- No instruction‑following capabilities
- No vision support
- Requires 8K context for best performance
Best for
- Local code generation
- Math problem solving
- Rapid prototyping on low‑VRAM GPUs
Who it’s for. Researchers and developers who need a small, efficient model for code and math tasks. The model is suitable for local deployment with llama.cpp or LM Studio.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 1.5 GB | 2.7 GB | Fits | Get file → | |
| Q4_0 | 1.5 GB | 2.7 GB | Fits | Get file → | |
| IQ2_M | 1.5 GB | 2.7 GB | Fits | Get file → | |
| IQ3_XS | 1.5 GB | 2.7 GB | Fits | Get file → | |
| Q2_K | 1.5 GB | 2.7 GB | Fits | Get file → | |
| IQ4_NL | 1.5 GB | 2.7 GB | Fits | Get file → | |
| IQ4_XS | 1.5 GB | 2.7 GB | Fits | Get file → | |
| IQ3_M | 1.5 GB | 2.7 GB | Fits | Get file → | |
| Q3_K_M | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q2_K_L | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q4_1 | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_L | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_XL | 1.7 GB | 2.9 GB | Fits | Get file → | |
| Q4_K_S | 1.7 GB | 3.0 GB | Fits | Get file → | |
| Q4_K_M | 1.8 GB | 3.1 GB | Fits | Get file → | |
| Q5_K_S | 1.9 GB | 3.1 GB | Fits | Get file → | |
| Q4_K_L | 1.9 GB | 3.1 GB | Fits | Get file → | |
| Q5_K_M | 2.0 GB | 3.2 GB | Fits | Get file → | |
| Q5_K_L | 2.0 GB | 3.2 GB | Fits | Get file → | |
| Q6_K | 2.6 GB | 3.8 GB | Fits | Get file → | |
| Q6_K_L | 2.6 GB | 3.8 GB | Fits | Get file → | |
| Q8_0 | 2.6 GB | 3.8 GB | Fits | Get file → | |
| F16 | 4.9 GB | 6.1 GB | Fits | Get file → | |
| F32 | 9.7 GB | 10.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (1.47 GB, 2.7 GB memory at 8K context) or Q3_K_S (1.46 GB, 2.7 GB memory). If 4 GB VRAM is available, Q3_K_S is the smallest option. For higher quality, Q4_K_M (1.85 GB, 3.1 GB memory) is recommended.
What GPU do you need for YuLan Mini?
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 (2.6 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (2.6 GB file, about 3.8 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (4.9 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is F32 (9.7 GB file, about 10.9 GB in use).
Which YuLan Mini quant should you choose?
Q4_K_M is the usual starting point for YuLan Mini: it balances file size and quality well. Here it is a 1.8 GB file.
The Q8_0 file is 2.6 GB, about 1.4 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 Q3_K_S at 1.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about YuLan Mini
How much VRAM does YuLan Mini need?
About 3.1 GB at Q4_K_M with an 8K context window. That is the 1.8 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 YuLan Mini on an 8 GB GPU?
Yes, with F16: the 4.9 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of YuLan Mini GGUF?
It depends on the quant: Q3_K_S is 1.5 GB, Q4_0 is 1.5 GB, IQ2_M is 1.5 GB, IQ3_XS is 1.5 GB, Q2_K is 1.5 GB, IQ4_NL is 1.5 GB and 18 more.
What context length does YuLan Mini support?
The GGUF header lists a trained context length of 28,723 tokens (28K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.5 GB at 28K.
Where can I download YuLan Mini GGUF?
The files are on Hugging Face in the bartowski/YuLan-Mini-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 YuLan Mini use?
Hugging Face lists the license as mit. 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 YuLan Mini on 8 GB VRAM?
Yes, the Q4_0 or Q3_K_S quantizations fit within 8 GB VRAM and use about 2.7 GB of memory at 8K context.
Does YuLan Mini support image input?
No, the model has no vision capabilities and is a text‑only model.
Is there an instruction‑following version of YuLan Mini?
No, the base model does not include instruction‑following; it is a pre‑trained language model only.