SmolLM2 1.7B Instruct Abliterated needs about 3.2 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 13 quants, from 0.7 GB (Q2_K) to 3.4 GB (F16).
SmolLM2 1.7B Instruct Abliterated – compact instruction model
SmolLM2 1.7B Instruct Abliterated is a 1.71‑billion‑parameter llama‑based model trained on 8192 context tokens. It is released under the apache‑2.0 license and available in multiple GGUF quantizations.
Good at
- Instruction following
- Compact size
- Low‑memory inference
Limits
- No vision support
- Limited context to 8192 tokens
- Requires GGUF quant file
Best for
- Local chatbot deployment
- Quick prototyping
- Edge inference
Who it’s for. Developers needing a small, instruction‑capable model for local use. Researchers testing llama‑based architectures with limited GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.7 GB | 2.8 GB | Fits | Get file → | |
| Q3_K_S | 0.8 GB | 2.9 GB | Fits | Get file → | |
| Q3_K_M | 0.9 GB | 3.0 GB | Fits | Get file → | |
| Q3_K_L | 0.9 GB | 3.0 GB | Fits | Get file → | |
| IQ4_XS | 0.9 GB | 3.1 GB | Fits | Get file → | |
| Q4_0 | 1.0 GB | 3.1 GB | Fits | Get file → | |
| Q4_K_S | 1.0 GB | 3.1 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 3.2 GB | Fits | Get file → | |
| Q5_K_S | 1.2 GB | 3.3 GB | Fits | Get file → | |
| Q5_K_M | 1.2 GB | 3.3 GB | Fits | Get file → | |
| Q6_K | 1.4 GB | 3.5 GB | Fits | Get file → | |
| Q8_0 | 1.8 GB | 3.9 GB | Fits | Get file → | |
| F16 | 3.4 GB | 5.5 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.06 GB file, ~3.2 GB memory). For 4 GB VRAM, use Q3_K_S (0.78 GB file, ~2.9 GB memory). For 2 GB VRAM, use Q2_K (0.67 GB file, ~2.8 GB memory). Estimates are approximate.
What GPU do you need for SmolLM2 1.7B Instruct Abliterated?
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 (1.8 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.4 GB file, about 5.5 GB in use).
Which SmolLM2 1.7B Instruct Abliterated quant should you choose?
Q4_K_M is the usual starting point for SmolLM2 1.7B Instruct Abliterated: it balances file size and quality well. Here it is a 1.1 GB file.
The Q8_0 file is 1.8 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 0.7 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
Frequently asked questions about SmolLM2 1.7B Instruct Abliterated
How much VRAM does SmolLM2 1.7B Instruct Abliterated need?
About 3.2 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 SmolLM2 1.7B Instruct Abliterated on an 8 GB GPU?
Yes, with F16: the 3.4 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of SmolLM2 1.7B Instruct Abliterated GGUF?
It depends on the quant: Q2_K is 0.7 GB, Q3_K_S is 0.8 GB, Q3_K_M is 0.9 GB, Q3_K_L is 0.9 GB, IQ4_XS is 0.9 GB, Q4_0 is 1.0 GB and 7 more.
What context length does SmolLM2 1.7B Instruct Abliterated support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.6 GB at 8K and 1.6 GB at 8K.
Where can I download SmolLM2 1.7B Instruct Abliterated GGUF?
The files are on Hugging Face in the mradermacher/SmolLM2-1.7B-Instruct-abliterated-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 SmolLM2 1.7B Instruct Abliterated 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 this model on 8 GB VRAM?
Yes, using Q4_K_M or Q4_K_S quantizations will fit within 8 GB VRAM with approximate 3.1‑3.2 GB usage.
Does this model support vision tasks?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the apache‑2.0 license.