IQuest Q1 needs about 197.5 GB of memory at Q4_K_M (a 194.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 9.4 GB (BF16) to 640.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.
IQuest Q1 – a 320B Mixture‑of‑Experts model for agentic coding and reasoning
IQuest Q1 is a 320B parameter MoE model designed for agentic coding, reasoning, and multi‑step tool use. It activates about 15B parameters per token and supports a 524288‑token context window. The model is text‑only and requires a patched llama.cpp to run.
Good at
- Agentic coding
- Multi‑step tool use
- Large context reasoning
Limits
- Text‑only input
- Requires patched llama.cpp
- No native vision support
Best for
- Complex coding tasks
- Tool‑integrated agent workflows
- Long‑form reasoning
Who it’s for. Developers building agentic applications that need large‑context reasoning and tool integration. Researchers exploring MoE architectures with high parameter counts.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 9.4 GB | 12.8 GB | Too big | Get file → | |
| Q4_K_M | 194.0 GB (16 parts) | 197.5 GB | Too big | Get file → | |
| BF16 | 640.8 GB (16 parts) | 644.2 GB | Too big | Get file → |
For 8‑GB VRAM, use the BF16 9.36‑GB file (memory ~12.8‑GB). For 16‑GB VRAM, use the Q4_K_M 194‑GB file (memory ~197.5‑GB). For 32‑GB or more, use the BF16 640.8‑GB file (memory ~644.2‑GB). Estimates are approximate.
What GPU do you need for IQuest Q1?
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: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is BF16 (9.4 GB file, about 12.8 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (9.4 GB file, about 12.8 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (9.4 GB file, about 12.8 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (9.4 GB file, about 12.8 GB in use).
Which IQuest Q1 quant should you choose?
Q4_K_M is the usual starting point for IQuest Q1: it balances file size and quality well. Here it is a 194.0 GB file.
If memory is tight, the smallest file is BF16 at 9.4 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about IQuest Q1
How much VRAM does IQuest Q1 need?
About 197.5 GB at Q4_K_M with an 8K context window. That is the 194.0 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 IQuest Q1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of IQuest Q1 GGUF?
It depends on the quant: BF16 is 9.4 GB, Q4_K_M is 194.0 GB, BF16 is 640.8 GB.
What context length does IQuest Q1 support?
The GGUF header lists a trained context length of 524,288 tokens (512K). The KV cache grows with the context you use: about 3.0 GB at 8K and 11.8 GB at 32K.
Where can I download IQuest Q1 GGUF?
The files are on Hugging Face in the xhxlb/IQuest-Q1-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 IQuest Q1 use?
Hugging Face lists the license as other. 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 IQuest Q1 on 8 GB VRAM?
No. The smallest quant requires 12.8‑GB VRAM at 8K context.
Does IQuest Q1 support image input?
No. It is text‑only and has no native image, audio, or video capability.
How many experts are activated per token?
Approximately 15B parameters are activated per token.