OculusMind-ToolCall-8B-v2 (Pico V2) needs about 10.7 GB of memory at Q8_0 (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.
Tool‑calling LLM with 8.49B parameters, 256k context, no vision
OculusMind-ToolCall-8B-v2 (Pico V2) is a 8.49B‑parameter Mistral‑3 model fine‑tuned for tool calling. It supports 256k context tokens and runs on a laptop with 10.7 GB VRAM at 8k context. The model is licensed under Apache‑2.0.
Good at
- Tool calling with 95.45 % accuracy
- Zero looping on tool turns
- Long‑context reading up to 250K tokens
Limits
- No vision support
- Requires 10.7 GB VRAM at 8k context
- Apache‑2.0 license only
Best for
- Tool‑based assistant agents
- Production‑grade agentic workflows
- Long‑context reasoning tasks
Who it’s for. Developers building lightweight, tool‑calling assistants for constrained hardware. The model is suitable for local deployment on laptops and embedded systems.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 9.0 GB | 10.7 GB | Too big | Get file → |
The only available GGUF quant is Q8_0, 9.03 GB file size. It requires approximately 10.7 GB VRAM at 8k context. Use this quant if your GPU has at least 10 GB VRAM; otherwise a larger quant is not available.
What GPU do you need for OculusMind-ToolCall-8B-v2 (Pico V2)?
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: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q8_0 (9.0 GB file, about 10.7 GB in use).
Which OculusMind-ToolCall-8B-v2 (Pico V2) quant should you choose?
Q8_0 (9.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about OculusMind-ToolCall-8B-v2 (Pico V2)
How much VRAM does OculusMind-ToolCall-8B-v2 (Pico V2) need?
About 10.7 GB at Q8_0 with an 8K context window. That is the 9.0 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 OculusMind-ToolCall-8B-v2 (Pico V2) on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of OculusMind-ToolCall-8B-v2 (Pico V2) GGUF?
It depends on the quant: Q8_0 is 9.0 GB.
What context length does OculusMind-ToolCall-8B-v2 (Pico V2) 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 4.6 GB at 32K.
Where can I download OculusMind-ToolCall-8B-v2 (Pico V2) GGUF?
The files are on Hugging Face in the OculusMindAI/OculusMind-ToolCall-8B-v2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does OculusMind-ToolCall-8B-v2 (Pico V2) 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?
The Q8_0 build requires about 10.7 GB VRAM at 8k context, so 8 GB VRAM is insufficient.
Does this model support image input?
No, the current release does not include the vision encoder.
What license does it use?
The model is released under the Apache‑2.0 license.