Wrench 9B Q4 K M needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Wrench 9B Q4 K M – a tool‑calling agentic model
Wrench 9B Q4 K M is a LoRA fine‑tuned version of Qwen3.5‑9B, designed for tool calling, error recovery, and system prompt following. It is a causal language model with a vision encoder and a native context length of 262,144 tokens. The model is available in a Q4_K_M quantized GGUF file that runs on 8 GB VRAM.
Good at
- Tool calling
- Error recovery
- System prompt following
Limits
- No vision support in this quant
- Requires 8 GB VRAM for full model
- License is apache‑2.0
Best for
- Agentic applications
- Tool‑integrated workflows
- Prompt‑driven automation
Who it’s for. Developers building AI agents that need reliable tool usage and robust error handling. The model is suitable for projects that can run on 8 GB VRAM and require a lightweight, quantized inference setup.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → |
The Q4_K_M quantized file is 5.63 GB and estimates 7.2 GB of VRAM at an 8 k context. For 8 GB VRAM systems, this quant is recommended. If more VRAM is available, a higher‑precision quant could be considered, but the provided file meets the 8 GB requirement.
What GPU do you need for Wrench 9B Q4 K M?
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: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is Q4_K_M (5.6 GB file, about 7.2 GB in use).
Which Wrench 9B Q4 K M quant should you choose?
Q4_K_M is the usual starting point for Wrench 9B Q4 K M: it balances file size and quality well. Here it is a 5.6 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Wrench 9B Q4 K M
How much VRAM does Wrench 9B Q4 K M need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 Wrench 9B Q4 K M on an 8 GB GPU?
Yes, with Q4_K_M: the 5.6 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Wrench 9B Q4 K M GGUF?
It depends on the quant: Q4_K_M is 5.6 GB.
What context length does Wrench 9B Q4 K M 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 4.3 GB at 32K.
Where can I download Wrench 9B Q4 K M GGUF?
The files are on Hugging Face in the ClankLabs/Wrench-9B-Q4_K_M-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 Wrench 9B Q4 K M 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 Wrench 9B on 8 GB VRAM?
Yes, the Q4_K_M quantized model is designed to run on 8 GB VRAM and is the recommended configuration.
Does this model support vision tasks?
No, the provided quant does not include vision support.
What license does Wrench 9B use?
The model is licensed under apache‑2.0.