DASD-4B-Thinking needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 0.0 GB to 8.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
4B dense model for long chain‑of‑thought reasoning
DASD-4B‑Thinking is a 4.02B parameter dense language model built on Qwen3 architecture. It is specialized for long chain‑of‑thought reasoning in mathematics, code, and science. The model is post‑trained from Qwen3‑4B‑Instruct‑2507 and distilled from gpt‑oss‑120b.
Good at
- Long chain‑of‑thought reasoning
- Mathematics and code generation
- Scientific reasoning
Limits
- No vision support
- Requires large VRAM for higher precision quants
- Apache‑2.0 license only
Best for
- Researchers needing reasoning on consumer GPUs
- Educational tools for math and coding
- Scientific hypothesis generation
Who it’s for. Developers and researchers who need a compact model capable of long‑form reasoning without large datasets. The model runs on consumer hardware with sufficient VRAM and is suitable for educational or research environments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.7 GB | Fits | Get file → | |
| IQ2_XXS | 1.5 GB | 3.2 GB | Fits | Get file → | |
| IQ2_XS | 1.5 GB | 3.3 GB | Fits | Get file → | |
| IQ2_S | 1.6 GB | 3.4 GB | Fits | Get file → | |
| IQ2_M | 1.7 GB | 3.4 GB | Fits | Get file → | |
| Q2_K_S | 1.7 GB | 3.4 GB | Fits | Get file → | |
| Q2_K_M | 1.7 GB | 3.4 GB | Fits | Get file → | |
| IQ3_XXS | 1.8 GB | 3.6 GB | Fits | Get file → | |
| IQ3_XS | 1.9 GB | 3.6 GB | Fits | Get file → | |
| IQ3_M | 2.1 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_S | 2.2 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_M | 2.2 GB | 4.0 GB | Fits | Get file → | |
| Q4_0 | 2.3 GB | 4.0 GB | Fits | Get file → | |
| IQ4_XS | 2.3 GB | 4.0 GB | Fits | Get file → | |
| IQ4_NL | 2.3 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_S | 2.4 GB | 4.1 GB | Fits | Get file → | |
| Q4_1 | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_M | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q5_0 | 2.8 GB | 4.5 GB | Fits | Get file → | |
| Q5_1 | 3.0 GB | 4.7 GB | Fits | Get file → | |
| Q8_0 | 4.3 GB | 6.0 GB | Fits | Get file → | |
| BF16 | 5.9 GB | 7.6 GB | Tight | Get file → | |
| F16 | 5.9 GB | 7.6 GB | Tight | Get file → | |
| BF16 | 8.1 GB | 9.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XXS (1.46 GB, 3.2 GB memory) or IQ3_XXS (1.85 GB, 3.6 GB memory). For 12 GB VRAM, Q4_K_S (2.41 GB, 4.1 GB memory) or Q5_0 (2.77 GB, 4.5 GB memory) are good options. Higher precision quants like Q8_0 (4.28 GB, 6 GB memory) require more VRAM.
What GPU do you need for DASD-4B-Thinking?
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 IQ4_NL (2.3 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (5.9 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (8.1 GB file, about 9.8 GB in use).
Which DASD-4B-Thinking quant should you choose?
Q4_K_M is the usual starting point for DASD-4B-Thinking: it balances file size and quality well. Here it is a 2.5 GB file.
The Q8_0 file is 4.3 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 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 DASD-4B-Thinking
How much VRAM does DASD-4B-Thinking need?
About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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 DASD-4B-Thinking on an 8 GB GPU?
Yes, with BF16: the 5.9 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of DASD-4B-Thinking GGUF?
It depends on the quant: file is 0.0 GB, IQ2_XXS is 1.5 GB, IQ2_XS is 1.5 GB, IQ2_S is 1.6 GB, IQ2_M is 1.7 GB, Q2_K_S is 1.7 GB and 18 more.
What context length does DASD-4B-Thinking support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download DASD-4B-Thinking GGUF?
The files are on Hugging Face in the Mungert/DASD-4B-Thinking-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 DASD-4B-Thinking 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 DASD-4B-Thinking on 8 GB VRAM?
Yes, with low‑bit quants such as IQ2_XXS or IQ3_XXS the model fits within 8 GB VRAM.
Does the model support vision tasks?
No, the model has no vision capabilities.
What license does the model use?
The model is released under the Apache‑2.0 license.