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 – 2.4B parameter language model
YuLan Mini is a 2.42B parameter model trained on 1.08T tokens. It is a lightweight base model without instruction‑following. The model performs well in mathematics and code generation.
Good at
- Mathematics
- Code generation
- Lightweight inference
Limits
- No instruction following
- Context limited to 28,723 tokens
- No vision support
Best for
- Code completion
- Math problem solving
- Low‑memory inference
Who it’s for. Researchers and developers needing a small, efficient language model for code and math tasks. The model is open‑source under the MIT license and can be run 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 or Q3_K_S (≈2.7 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (≈3.1 GB) or Q5_K_M (≈3.2 GB) are suitable. For 16 GB VRAM, Q6_K or Q8_0 (≈3.8 GB) provide higher precision.
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 diskrot/YuLan-Mini-GGUF-diskrot 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, use Q4_0 or Q3_K_S quantizations, which require about 2.7 GB memory at 8 k context.
Does YuLan Mini support instruction following?
No, it is a pre‑trained base model without instruction‑following capabilities.
What is the maximum context length for YuLan Mini?
The model is trained with a context of 28,723 tokens, which is the practical limit.