Javi0.3 2B needs about 2.2 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 16 quants, from 0.0 GB to 1.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.
Javi0.3 2B – a 2B agent model for tool‑based reasoning
Javi0.3 2B is a 1.94B parameter model fine‑tuned from Qwen3.5‑2B for coding and research agents. It is trained to use tools effectively and to avoid guessing. The model is available in multiple GGUF quantizations for llama.cpp and lmswitch.
Good at
- Tool‑based reasoning
- Short, grounded answers
- Avoids looping
Limits
- No vision support
- Requires tool access for time‑sensitive queries
- Large context size 262144 tokens
Best for
- Agent workflows with web search
- Coding assistance with tool calls
- Research queries needing verification
Who it’s for. Developers building agent systems that rely on web search, page fetch, or shell tools. The model is suited for environments where the user can supply a low‑temperature prompt and enable thinking off.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.9 GB | Fits | Get file → | |
| Q2_K | 1.0 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_S | 1.0 GB | 2.0 GB | Fits | Get file → | |
| IQ3_S | 1.1 GB | 2.0 GB | Fits | Get file → | |
| IQ3_M | 1.1 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_M | 1.1 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_L | 1.2 GB | 2.1 GB | Fits | Get file → | |
| IQ4_XS | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q4_0 | 1.2 GB | 2.2 GB | Fits | Get file → | |
| Q4_K_S | 1.2 GB | 2.2 GB | Fits | Get file → | |
| IQ4_NL | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q4_K_M | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q4_1 | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q5_K_S | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_M | 1.5 GB | 2.4 GB | Fits | Get file → | |
| Q6_K | 1.6 GB | 2.5 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.31 GB, ~2.2 GB memory at 8 k context). For 4 GB VRAM, Q3_K_S (1.05 GB, ~2 GB memory) is a good balance. If memory is very tight, Q2_K (0.99 GB, ~1.9 GB memory) can run with 8 k context.
What GPU do you need for Javi0.3 2B?
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 (1.6 GB file, about 2.5 GB in use).
Which Javi0.3 2B quant should you choose?
Q4_K_M is the usual starting point for Javi0.3 2B: it balances file size and quality well. Here it is a 1.3 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 Javi0.3 2B
How much VRAM does Javi0.3 2B need?
About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.3 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 Javi0.3 2B on an 8 GB GPU?
Yes, with Q6_K: the 1.6 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Javi0.3 2B GGUF?
It depends on the quant: file is 0.0 GB, Q2_K is 1.0 GB, Q3_K_S is 1.0 GB, IQ3_S is 1.1 GB, IQ3_M is 1.1 GB, Q3_K_M is 1.1 GB and 10 more.
What context length does Javi0.3 2B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.
Where can I download Javi0.3 2B GGUF?
The files are on Hugging Face in the mradermacher/Javi0.3-2B-i1-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 Javi0.3 2B 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 Javi0.3 2B on 8 GB VRAM?
Yes, using a Q4_K_M quantization (1.31 GB file) will fit within 8 GB VRAM with an estimated 2.2 GB memory usage at 8 k context.
Does the model support image input?
No, Javi0.3 2B was never trained or evaluated on images and has no vision tower.
What license applies to this model?
The model is released under the apache-2.0 license.