Llasa 3b needs about 3.6 GB of memory at Q4_K_M (a 2.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 49 quants, from 0.0 GB to 3.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Llasa 3b – 3.41B parameter llama model with tool usage
Llasa 3b is a 3.41B parameter llama architecture model. It supports tool usage and is trained on 131072 context tokens. The model is available in multiple GGUF quantizations.
Good at
- Tool integration
- Large context handling
- Flexible quant options
Limits
- No vision support
- License not specified
- Requires 8k context for memory estimates
Best for
- Chatbot development
- Tool‑enabled assistants
- Context‑heavy inference
Who it’s for. Developers building conversational agents that need tool integration and large context windows. Suitable for those who can manage the memory requirements of the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.4 GB | Fits | Get file → | |
| IQ1_S | 1.0 GB | 2.4 GB | Fits | Get file → | |
| IQ1_M | 1.1 GB | 2.5 GB | Fits | Get file → | |
| IQ2_XXS | 1.2 GB | 2.6 GB | Fits | Get file → | |
| IQ1_S | 1.2 GB | 2.6 GB | Fits | Get file → | |
| IQ2_XS | 1.2 GB | 2.7 GB | Fits | Get file → | |
| IQ1_M | 1.3 GB | 2.7 GB | Fits | Get file → | |
| IQ2_S | 1.3 GB | 2.7 GB | Fits | Get file → | |
| IQ2_XXS | 1.4 GB | 2.8 GB | Fits | Get file → | |
| IQ2_M | 1.4 GB | 2.8 GB | Fits | Get file → | |
| IQ2_XS | 1.4 GB | 2.9 GB | Fits | Get file → | |
| Q2_K_S | 1.4 GB | 2.9 GB | Fits | Get file → | |
| IQ3_XXS | 1.5 GB | 2.9 GB | Fits | Get file → | |
| Q2_K | 1.5 GB | 3.0 GB | Fits | Get file → | |
| IQ2_S | 1.6 GB | 3.0 GB | Fits | Get file → | |
| IQ2_M | 1.6 GB | 3.1 GB | Fits | Get file → | |
| Q2_K_S | 1.6 GB | 3.1 GB | Fits | Get file → | |
| IQ3_XS | 1.6 GB | 3.1 GB | Fits | Get file → | |
| IQ3_S | 1.7 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_S | 1.7 GB | 3.1 GB | Fits | Get file → | |
| Q2_K | 1.7 GB | 3.2 GB | Fits | Get file → | |
| IQ3_XXS | 1.7 GB | 3.2 GB | Fits | Get file → | |
| IQ3_M | 1.8 GB | 3.2 GB | Fits | Get file → | |
| Q3_K_M | 1.9 GB | 3.3 GB | Fits | Get file → | |
| IQ3_XS | 1.9 GB | 3.3 GB | Fits | Get file → | |
| IQ3_S | 2.0 GB | 3.4 GB | Fits | Get file → | |
| Q3_K_S | 2.0 GB | 3.4 GB | Fits | Get file → | |
| Q3_K_L | 2.0 GB | 3.4 GB | Fits | Get file → | |
| IQ4_XS | 2.0 GB | 3.4 GB | Fits | Get file → | |
| IQ3_M | 2.0 GB | 3.5 GB | Fits | Get file → | |
| IQ4_NL | 2.1 GB | 3.5 GB | Fits | Get file → | |
| Q4_0 | 2.1 GB | 3.5 GB | Fits | Get file → | |
| Q4_K_S | 2.1 GB | 3.5 GB | Fits | Get file → | |
| Q3_K_M | 2.1 GB | 3.5 GB | Fits | Get file → | |
| Q4_K_M | 2.2 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_L | 2.2 GB | 3.7 GB | Fits | Get file → | |
| Q4_1 | 2.3 GB | 3.7 GB | Fits | Get file → | |
| IQ4_XS | 2.3 GB | 3.8 GB | Fits | Get file → | |
| IQ4_NL | 2.4 GB | 3.9 GB | Fits | Get file → | |
| Q4_0 | 2.4 GB | 3.9 GB | Fits | Get file → | |
| Q4_K_S | 2.4 GB | 3.9 GB | Fits | Get file → | |
| Q5_K_S | 2.4 GB | 3.9 GB | Fits | Get file → | |
| Q5_K_M | 2.5 GB | 3.9 GB | Fits | Get file → | |
| Q4_K_M | 2.5 GB | 4.0 GB | Fits | Get file → | |
| Q4_1 | 2.6 GB | 4.1 GB | Fits | Get file → | |
| Q6_K | 2.8 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_S | 2.8 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_M | 2.9 GB | 4.3 GB | Fits | Get file → | |
| Q6_K | 3.3 GB | 4.7 GB | Fits | Get file → |
For 8 GB VRAM use Q4_K_M (2.19 GB file, 3.6 GB memory at 8k context). For 12 GB VRAM use Q5_K_M (2.49 GB file, 3.9 GB memory). For 16 GB VRAM use Q6_K (3.3 GB file, 4.7 GB memory). Estimates are approximate.
What GPU do you need for Llasa 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 Q4_K_M (2.5 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.3 GB file, about 4.7 GB in use).
Which Llasa 3b quant should you choose?
Q4_K_M is the usual starting point for Llasa 3b: it balances file size and quality well. Here it is a 2.2 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Llasa 3b
How much VRAM does Llasa 3b need?
About 3.6 GB at Q4_K_M with an 8K context window. That is the 2.2 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 Llasa 3b on an 8 GB GPU?
Yes, with Q6_K: the 3.3 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Llasa 3b GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.0 GB, IQ1_M is 1.1 GB, IQ2_XXS is 1.2 GB, IQ1_S is 1.2 GB, IQ2_XS is 1.2 GB and 43 more.
What context length does Llasa 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 Llasa 3b GGUF?
The files are on Hugging Face in the mradermacher/llasa-3b-i1-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 Llasa 3b on 8 GB VRAM?
Yes, using the Q4_K_M quantization which requires about 3.6 GB of VRAM at 8k context.
Does Llasa 3b support vision?
No, the model does not include vision capabilities.
What is the largest context length Llasa 3b supports?
It was trained on 131072 context tokens.