doosra qwen3.5 4b toolcalls a needs about 4.4 GB of memory at Q4_K_M (a 2.8 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 4.4 GB.
Qwen3.5 4B fine‑tuned for cricket tool‑calling
Doosra Qwen3.5 4B is a 4.33B‑parameter model fine‑tuned on 5,854 tool‑calling conversations. It uses a cricket analytics toolkit with 25 tools and 11 million balls of Cricsheet data. The prompt is about 8× shorter than general models, around 280 tokens.
Good at
- Tool‑calling with cricket analytics
- Short prompt generation
- Multimodal reasoning
Limits
- Requires ~4.4 GB VRAM at 8 k context
- No external vision support beyond built‑in tool calls
- Apache‑2.0 license
Best for
- Cricket analytics apps
- Local AI copilots for sports data
- Tool‑based question answering
Who it’s for. Developers building cricket analytics applications or local AI assistants that need efficient tool‑calling and short prompts. The model is suitable for laptops and small servers with limited VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.8 GB | 4.4 GB | Fits | Get file → |
The only available quant is Q4_K_M, 2.78 GB file size. It needs about 4.4 GB VRAM at 8 k context. For 8 GB VRAM you can run it comfortably. If VRAM is lower, no other quant is provided.
What GPU do you need for doosra qwen3.5 4b toolcalls a?
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 Q4_K_M (2.8 GB file, about 4.4 GB in use).
Which doosra qwen3.5 4b toolcalls a quant should you choose?
Q4_K_M is the usual starting point for doosra qwen3.5 4b toolcalls a: it balances file size and quality well. Here it is a 2.8 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about doosra qwen3.5 4b toolcalls a
How much VRAM does doosra qwen3.5 4b toolcalls a need?
About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.8 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 doosra qwen3.5 4b toolcalls a on an 8 GB GPU?
Yes, with Q4_K_M: the 2.8 GB file needs about 4.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of doosra qwen3.5 4b toolcalls a GGUF?
It depends on the quant: Q4_K_M is 2.8 GB.
What context length does doosra qwen3.5 4b toolcalls a support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.
Where can I download doosra qwen3.5 4b toolcalls a GGUF?
The files are on Hugging Face in the Sarthak213/doosra-qwen3.5-4b-toolcalls-a repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does doosra qwen3.5 4b toolcalls a 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 this model on 8 GB VRAM?
Yes. The Q4_K_M quant requires about 4.4 GB VRAM at 8 k context, so 8 GB is sufficient.
Does it support vision?
Yes, it has vision capability as part of its multimodal design.
What license does it use?
Apache‑2.0.