Parable SmolLM3 3B Claude Fable 5 needs about 3.0 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 1.9 GB (Q4_K_M) to 6.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.
Parable SmolLM3 3B Claude Fable 5 – a small, reasoning‑focused LLM
Parable SmolLM3 3B Claude Fable 5 is a 3.08 billion‑parameter decoder‑only model based on SmolLM3. It is fine‑tuned on real Claude Fable 5 agent transcripts and supports long context up to 128k tokens. The model is released under Apache‑2.0 and is fully open.
Good at
- Hybrid reasoning with step‑by‑step thinking
- Long‑context generation up to 128k tokens
- Multilingual support in six languages
Limits
- No vision or multimodal capabilities
- Requires at least 8 k context for memory estimates
- Apache‑2.0 license restricts commercial redistribution without attribution
Best for
- Building local coding assistants that reason before answering
- Generating long documents with consistent context
- Fine‑tuning for domain‑specific reasoning tasks
Who it’s for. Developers and researchers who need a lightweight, open‑source LLM capable of extended reasoning and long‑context generation. The model is ideal for local deployment on machines with moderate GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.9 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_M | 2.2 GB | 3.3 GB | Fits | Get file → | |
| Q6_K | 2.5 GB | 3.6 GB | Fits | Get file → | |
| Q8_0 | 3.3 GB | 4.4 GB | Fits | Get file → | |
| F16 | 6.2 GB | 7.3 GB | Tight | Get file → |
For 8 GB VRAM, the Q4_K_M quant (1.92 GB file, ~3 GB memory at 8k context) is recommended. If 12 GB VRAM is available, Q5_K_M (2.21 GB file, ~3.3 GB memory) offers a balance of quality and size. For higher precision, Q8_0 (3.28 GB file, ~4.4 GB memory) can be used on 16 GB VRAM systems.
What GPU do you need for Parable SmolLM3 3B Claude Fable 5?
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 Q6_K (2.5 GB file, about 3.6 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.4 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (6.2 GB file, about 7.3 GB in use).
Which Parable SmolLM3 3B Claude Fable 5 quant should you choose?
Q4_K_M is the usual starting point for Parable SmolLM3 3B Claude Fable 5: it balances file size and quality well. Here it is a 1.9 GB file.
The Q8_0 file is 3.3 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Parable SmolLM3 3B Claude Fable 5
How much VRAM does Parable SmolLM3 3B Claude Fable 5 need?
About 3.0 GB at Q4_K_M with an 8K context window. That is the 1.9 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 Parable SmolLM3 3B Claude Fable 5 on an 8 GB GPU?
Yes, with F16: the 6.2 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Parable SmolLM3 3B Claude Fable 5 GGUF?
It depends on the quant: Q4_K_M is 1.9 GB, Q5_K_M is 2.2 GB, Q6_K is 2.5 GB, Q8_0 is 3.3 GB, F16 is 6.2 GB.
What context length does Parable SmolLM3 3B Claude Fable 5 support?
The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.4 GB at 32K.
Where can I download Parable SmolLM3 3B Claude Fable 5 GGUF?
The files are on Hugging Face in the AnkitAI/Parable-SmolLM3-3B-Claude-Fable-5-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 Parable SmolLM3 3B Claude Fable 5 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 Parable SmolLM3 3B Claude Fable 5 on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 3 GB of VRAM at 8k context, leaving headroom for the GPU and other processes.
Does this model support image inputs?
No, the model is purely text‑based and does not include vision capabilities.
What context length can I use?
The model is trained on 64k tokens and supports up to 128k tokens with YARN extrapolation.