Qwen3 4b toolcall gguf llamacpp codex needs about 6.0 GB of memory at its main file (a 4.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Qwen3 4B toolcall model for local inference
Qwen3 4B toolcall is a 4.02B parameter model fine‑tuned for function calling and tool usage. It supports a 262,144 token context window and is optimized for llama.cpp inference. The model is released under the MIT license.
Good at
- Tool calling
- Coding
- Long‑context reasoning
Limits
- No vision support
- Requires 6GB VRAM for full context
- MIT license limits commercial use
Best for
- Local tool‑based agents
- Code generation tasks
- Complex multi‑step queries
Who it’s for. Developers building local LLM agents that need reliable function calling and long‑context handling. Suitable for CPU/GPU inference with llama.cpp or similar frameworks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 4.3 GB | 6.0 GB | Fits | Get file → |
The provided GGUF file is 4.28GB and requires about 6GB of VRAM for full 262,144 token context. Use this file if you have at least 6GB VRAM. For lower VRAM budgets, reduce the context length to 32,768 tokens to lower memory usage.
What GPU do you need for Qwen3 4b toolcall gguf llamacpp codex?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is the main file (4.3 GB file, about 6.0 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwen3 4b toolcall gguf llamacpp codex
How much VRAM does Qwen3 4b toolcall gguf llamacpp codex need?
About 6.0 GB at its main file with an 8K context window. That is the 4.3 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 Qwen3 4b toolcall gguf llamacpp codex on an 8 GB GPU?
Yes, with the smaller files: the 4.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Qwen3 4b toolcall gguf llamacpp codex GGUF?
It depends on the quant: file is 4.3 GB.
What context length does Qwen3 4b toolcall gguf llamacpp codex support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download Qwen3 4b toolcall gguf llamacpp codex GGUF?
The files are on Hugging Face in the Manojb/Qwen3-4b-toolcall-gguf-llamacpp-codex repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Qwen3 4b toolcall gguf llamacpp codex use?
Hugging Face lists the license as mit. 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 this model on 8GB VRAM?
Yes, the model fits within 6GB VRAM for full context, leaving headroom for 8GB VRAM setups.
What is the context length of this model?
The model supports 262,144 tokens natively.
Under what license is this model released?
The model is released under the MIT license.