SmolLM 135M Instruct needs about 0.8 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 13 quants, from 0.1 GB (Q2_K) to 0.3 GB (F16).
SmolLM 135M Instruct – a lightweight instruction‑tuned LLM
SmolLM 135M Instruct is a 135M‑parameter instruction‑tuned model based on the llama architecture. It supports a 2048‑token context window and is released under the apache-2.0 license. The model is optimized for local inference with GGUF quantizations.
Good at
- Instruction following
- General knowledge queries
- Basic Python code generation
Limits
- English only
- Limited arithmetic accuracy
- No vision support
Best for
- Chatbots on edge devices
- Rapid prototyping of LLM apps
- Educational content generation
Who it’s for. Developers needing a small, fast LLM for local deployment. Researchers testing instruction‑tuned models in constrained environments. Educators building lightweight AI assistants.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q3_K_S | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q3_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q3_K_L | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_K_S | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q5_0 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q4_K_M | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q5_K_S | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q6_K | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| F16 | 0.3 GB | 0.8 GB | Fits | Get file → |
For 8 GB VRAM, use Q2_K or Q3_K_S (file size 0.09 GB, memory ~0.8 GB). If 16 GB VRAM is available, Q4_K_M or Q5_K_S (file size 0.11 GB) offers higher quality. The full F16 model (0.27 GB) requires ~1 GB memory and is best for higher‑quality inference on powerful GPUs.
What GPU do you need for SmolLM 135M Instruct?
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 F16 (0.3 GB file, about 1.0 GB in use).
Which SmolLM 135M Instruct quant should you choose?
Q4_K_M is the usual starting point for SmolLM 135M Instruct: it balances file size and quality well. Here it is a 0.1 GB file.
The Q8_0 file is 0.1 GB, about 1.4 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 0.1 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 SmolLM 135M Instruct
How much VRAM does SmolLM 135M Instruct need?
About 0.8 GB at Q4_K_M with an 8K context window. That is the 0.1 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 SmolLM 135M Instruct on an 8 GB GPU?
Yes, with F16: the 0.3 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of SmolLM 135M Instruct GGUF?
It depends on the quant: Q2_K is 0.1 GB, Q3_K_S is 0.1 GB, Q4_0 is 0.1 GB, Q3_K_M is 0.1 GB, Q3_K_L is 0.1 GB, Q4_K_S is 0.1 GB and 7 more.
What context length does SmolLM 135M Instruct support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.0 GB at 2K.
Where can I download SmolLM 135M Instruct GGUF?
The files are on Hugging Face in the second-state/SmolLM-135M-Instruct-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 SmolLM 135M Instruct 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 SmolLM 135M Instruct on 8 GB VRAM?
Yes, quantizations such as Q2_K or Q3_K_S use about 0.8 GB of VRAM at 8 k context, fitting comfortably on 8 GB.
What is the maximum context length?
The model supports a context length of 2048 tokens.
Is the model multilingual?
No, it is English only and may struggle with non‑English text.