SummLlama3.2 3B needs about 3.8 GB of memory at Q5_K_M (a 2.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
SummLlama3.2 3B – a summarization‑focused Llama3.2 model
SummLlama3.2 3B is a 3.21‑billion‑parameter Llama architecture fine‑tuned for summarization. It was trained with Direct Preference Optimization on over 100K summarization examples across seven domains. The model supports tool usage and is available in a single Q5_K_M quantized GGUF file.
Good at
- Faithful summarization
- Complete coverage of input
- Concise output
Limits
- No vision support
- License not specified
- Requires 8‑k context for memory estimate
Best for
- Generating article summaries
- Condensing meeting notes
- Creating concise reports
Who it’s for. Users needing a lightweight summarizer that balances faithfulness and brevity. Suitable for developers integrating summarization into applications via llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 2.3 GB | 3.8 GB | Fits | Get file → |
The only available quant is Q5_K_M with a file size of 2.32 GB. It requires approximately 3.8 GB of VRAM at 8‑k context. For systems with 4 GB VRAM, this quant is suitable; larger VRAM allows higher context lengths.
What GPU do you need for SummLlama3.2 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: the best quant that fits is Q5_K_M (2.3 GB file, about 3.8 GB in use).
Which SummLlama3.2 3B quant should you choose?
Q5_K_M (2.3 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about SummLlama3.2 3B
How much VRAM does SummLlama3.2 3B need?
About 3.8 GB at Q5_K_M with an 8K context window. That is the 2.3 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 SummLlama3.2 3B on an 8 GB GPU?
Yes, with Q5_K_M: the 2.3 GB file needs about 3.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of SummLlama3.2 3B GGUF?
It depends on the quant: Q5_K_M is 2.3 GB.
What context length does SummLlama3.2 3B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download SummLlama3.2 3B GGUF?
The files are on Hugging Face in the dil99x/SummLlama3.2-3B-Q5_K_M-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run SummLlama3.2 3B on 4 GB VRAM?
Yes, the Q5_K_M quant uses about 3.8 GB of VRAM at 8‑k context, fitting within a 4 GB budget.
Does this model support image inputs?
No, the model has no vision capabilities.
What context length does the model support?
The model was trained with 131072 tokens, but the provided quant estimate is for 8‑k context.