ReMask 3B needs about 4.9 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 1.1 GB (Q2_K) to 5.6 GB (F16).
ReMask 3B – a 2.8B parameter stablelm model fine‑tuned with SPIN
ReMask 3B is a 2.8B parameter stablelm model trained with Self‑Play Finetuning (SPIN). It is available in multiple GGUF quantizations and released under cc‑by‑sa‑4.0. The model supports a 4096 token context window.
Good at
- Fine‑tuned for autoregressive generation
- SPIN reduces exposure bias
- Stablelm architecture
Limits
- No vision support
- License requires attribution
- No mixture of experts
Best for
- Chat and text completion
- Prompt engineering experiments
- Educational demos
Who it’s for. Developers and researchers who need a lightweight, open‑source language model for local inference. The model is suitable for those who can run GGUF files on llama.cpp and respect the cc‑by‑sa‑4.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.1 GB | 2.9 GB | Fits | Get file → | |
| IQ3_XS | 1.2 GB | 3.0 GB | Fits | Get file → | |
| IQ3_S | 1.3 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_S | 1.3 GB | 3.1 GB | Fits | Get file → | |
| IQ3_M | 1.3 GB | 3.2 GB | Fits | Get file → | |
| Q3_K_M | 1.4 GB | 3.2 GB | Fits | Get file → | |
| Q3_K_L | 1.5 GB | 3.4 GB | Fits | Get file → | |
| IQ4_XS | 1.5 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_S | 1.6 GB | 3.5 GB | Fits | Get file → | |
| Q4_K_M | 1.7 GB | 3.6 GB | Fits | Get file → | |
| Q5_K_S | 1.9 GB | 3.8 GB | Fits | Get file → | |
| Q5_K_M | 2.0 GB | 3.8 GB | Fits | Get file → | |
| Q6_K | 2.3 GB | 4.1 GB | Fits | Get file → | |
| Q8_0 | 3.0 GB | 4.8 GB | Fits | Get file → | |
| F16 | 5.6 GB | 7.4 GB | Tight | Get file → |
For 8 GB VRAM, use Q4_K_M (1.71 GB file, 4.9 GB memory). For 12 GB VRAM, Q5_K_M (1.99 GB file, 5.2 GB memory) is a good balance. If more memory is available, Q8_0 (2.97 GB file, 6.2 GB memory) provides higher precision.
What GPU do you need for ReMask 3B?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q6_K (2.3 GB file, about 5.5 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.0 GB file, about 6.2 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (5.6 GB file, about 8.8 GB in use).
Which ReMask 3B quant should you choose?
Q4_K_M is the usual starting point for ReMask 3B: it balances file size and quality well. Here it is a 1.7 GB file.
The Q8_0 file is 3.0 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 1.1 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 ReMask 3B
How much VRAM does ReMask 3B need?
About 4.9 GB at Q4_K_M with an 8K context window. That is the 1.7 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 ReMask 3B on an 8 GB GPU?
Yes, with Q8_0: the 3.0 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ReMask 3B GGUF?
It depends on the quant: Q2_K is 1.1 GB, IQ3_XS is 1.2 GB, IQ3_S is 1.3 GB, Q3_K_S is 1.3 GB, IQ3_M is 1.3 GB, Q3_K_M is 1.4 GB and 9 more.
What context length does ReMask 3B support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.
Where can I download ReMask 3B GGUF?
The files are on Hugging Face in the mradermacher/ReMask-3B-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 ReMask 3B use?
Hugging Face lists the license as cc-by-sa-4.0. 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 ReMask 3B on 8 GB VRAM?
Yes, the Q4_K_M quant uses 4.9 GB estimated memory at 8k context, which fits within 8 GB VRAM.
Does ReMask 3B support image inputs?
No, the model has no vision capabilities.