DeepScaleR 1.5B Preview needs about 1.9 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 24 quants, from 0.8 GB (Q2_K) to 7.1 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.
DeepScaleR 1.5B Preview – a Qwen2‑based LLM with 1.78B parameters
DeepScaleR 1.5B Preview is a language model fine‑tuned from DeepSeek‑R1‑Distilled‑Qwen‑1.5B using reinforcement learning. It supports a context length of 131072 tokens and is released under the MIT license.
Good at
- Long‑context reasoning
- Math problem solving
- OpenAI Chat API compatibility
Limits
- No vision support
- Requires 8K context for memory estimates
- No partial reward training
Best for
- Educational math tutoring
- Competitive exam prep
- Research on RL‑trained LLMs
Who it’s for. Developers and researchers who need a small, long‑context model for reasoning tasks. The model is open source and can be run locally with llama.cpp or other inference engines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.8 GB | 1.5 GB | Fits | Get file → | |
| IQ3_XXS | 0.8 GB | 1.5 GB | Fits | Get file → | |
| IQ3_XS | 0.8 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_S | 0.9 GB | 1.6 GB | Fits | Get file → | |
| IQ3_M | 0.9 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_M | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q3_K_L | 1.0 GB | 1.7 GB | Fits | Get file → | |
| Q2_K_L | 1.0 GB | 1.7 GB | Fits | Get file → | |
| IQ4_XS | 1.0 GB | 1.8 GB | Fits | Get file → | |
| IQ4_NL | 1.1 GB | 1.8 GB | Fits | Get file → | |
| Q4_0 | 1.1 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_S | 1.1 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 1.9 GB | Fits | Get file → | |
| Q4_1 | 1.2 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_XL | 1.2 GB | 1.9 GB | Fits | Get file → | |
| Q5_K_S | 1.3 GB | 2.0 GB | Fits | Get file → | |
| Q5_K_M | 1.3 GB | 2.0 GB | Fits | Get file → | |
| Q4_K_L | 1.3 GB | 2.0 GB | Fits | Get file → | |
| Q5_K_L | 1.4 GB | 2.2 GB | Fits | Get file → | |
| Q6_K | 1.5 GB | 2.2 GB | Fits | Get file → | |
| Q6_K_L | 1.6 GB | 2.3 GB | Fits | Get file → | |
| Q8_0 | 1.9 GB | 2.6 GB | Fits | Get file → | |
| F16 | 3.6 GB | 4.3 GB | Fits | Get file → | |
| F32 | 7.1 GB | 7.8 GB | Tight | Get file → |
For 8 GB VRAM use Q2_K (0.75 GB) or IQ3_XXS (0.77 GB). For 12 GB VRAM use Q4_K_M (1.12 GB) or Q4_K_L (1.29 GB). For 16 GB VRAM use Q5_K_L (1.43 GB) or Q6_K_L (1.58 GB). Estimates are approximate.
What GPU do you need for DeepScaleR 1.5B Preview?
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 (1.9 GB file, about 2.6 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.6 GB file, about 4.3 GB in use).
- 8 GB VRAM: the best quant that fits is F32 (7.1 GB file, about 7.8 GB in use).
Which DeepScaleR 1.5B Preview quant should you choose?
Q4_K_M is the usual starting point for DeepScaleR 1.5B Preview: it balances file size and quality well. Here it is a 1.1 GB file.
The Q8_0 file is 1.9 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 DeepScaleR 1.5B Preview
How much VRAM does DeepScaleR 1.5B Preview need?
About 1.9 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 DeepScaleR 1.5B Preview on an 8 GB GPU?
Yes, with F32: the 7.1 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 DeepScaleR 1.5B Preview GGUF?
It depends on the quant: Q2_K is 0.8 GB, IQ3_XXS is 0.8 GB, IQ3_XS is 0.8 GB, Q3_K_S is 0.9 GB, IQ3_M is 0.9 GB, Q3_K_M is 0.9 GB and 18 more.
What context length does DeepScaleR 1.5B Preview support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.
Where can I download DeepScaleR 1.5B Preview GGUF?
The files are on Hugging Face in the bartowski/agentica-org_DeepScaleR-1.5B-Preview-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 DeepScaleR 1.5B Preview 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 DeepScaleR on 8 GB VRAM?
Yes, using Q2_K or IQ3_XXS quantizations, which are around 0.75–0.77 GB in size.
Does the model support image inputs?
No, DeepScaleR is a text‑only model with no vision capabilities.
What context length does it support?
The model is trained with a context length of 131072 tokens.