SmolLM2 1.7B Instruct heretic 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 15 quants, from 0.7 GB (Q2_K) to 3.4 GB (F16).
SmolLM2 1.7B Instruct heretic – a lightweight instruct model
SmolLM2 1.7B Instruct heretic is a 1.71B parameter Llama‑architecture model. It is decensored and has refusal behaviour suppressed. The model runs on consumer GPUs, laptops, and CPUs.
Good at
- Instruction following
- Function calling
- Text rewriting and summarization
Limits
- No vision support
- Requires 8k context for full performance
- Apache‑2.0 license
Best for
- Local agents
- Tool‑calling pipelines
- Code assistance on small hardware
Who it’s for. Developers who need a real instruct model that answers instead of declining, on hardware they already own. It is suitable for local agents, tool‑calling, rewriting and summarization pipelines, code assistance on small hardware, and as the instruction‑following half of a two‑model setup.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.7 GB | 2.8 GB | Fits | Get file → | |
| IQ3_S | 0.8 GB | 2.9 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 → | |
| Q4_1 | 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 at 8k context). For 4 GB VRAM, use Q3_K_S (0.78 GB file, 2.9 GB memory). For CPU or very low memory, use Q2_K (0.67 GB file, 2.8 GB memory).
What GPU do you need for SmolLM2 1.7B Instruct heretic?
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 heretic quant should you choose?
Q4_K_M is the usual starting point for SmolLM2 1.7B Instruct heretic: 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
Source
Frequently asked questions about SmolLM2 1.7B Instruct heretic
How much VRAM does SmolLM2 1.7B Instruct heretic 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 heretic 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 heretic GGUF?
It depends on the quant: Q2_K is 0.7 GB, IQ3_S is 0.8 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 and 9 more.
What context length does SmolLM2 1.7B Instruct heretic 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 heretic GGUF?
The files are on Hugging Face in the saidutta69/SmolLM2-1.7B-Instruct-heretic 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 heretic 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 SmolLM2 1.7B Instruct heretic on 8 GB VRAM?
Yes, the Q4_K_M quantized model is 1.06 GB and requires about 3.2 GB VRAM at 8k context.
Does this model support vision tasks?
No, the model has no vision capability.
What license does it use?
The model is released under the Apache‑2.0 license.