T Search needs about 14.2 GB of memory at its main file (a 13.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.
T Search – an agentic retriever built on Qwen3.6-35B-A3B
T Search is a 35.5‑billion‑parameter model designed for multi‑step search tasks in English and Russian. It plans, executes, and tracks search rounds, returning a ranked evidence set for downstream use. The model is trained on synthetic search tasks using the official T‑Search harness.
Good at
- Agentic multi‑round search
- Retrieval quality over base model
- Robustness across retriever configurations
Limits
- No vision support
- Requires 262144‑token context
- License is apache‑2.0
Best for
- Search‑driven QA systems
- Retrieval‑augmented generation
- Knowledge‑base querying
Who it’s for. Developers building search‑centric AI assistants or retrieval‑augmented pipelines. The model is suitable for applications needing structured evidence collection and ranking.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 13.0 GB | 14.2 GB | Too big | Get file → |
The only available GGUF quantization is unknown, with a file size of 13.03 GB. It estimates 14.2 GB of VRAM at an 8 k‑token context. For lower VRAM budgets, consider using a different model or a smaller context size, as no other quantizations are listed.
What GPU do you need for T Search?
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 the main file (13.0 GB file, about 14.2 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about T Search
How much VRAM does T Search need?
About 14.2 GB at its main file with an 8K context window. That is the 13.0 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 T Search on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of T Search GGUF?
It depends on the quant: file is 13.0 GB.
What context length does T Search support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.
Where can I download T Search GGUF?
The files are on Hugging Face in the IsValorum/T-Search-APEX-I-NanoPlus-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 T Search 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 T Search on 8 GB VRAM?
No. The model requires approximately 14.2 GB of VRAM at an 8 k‑token context, which exceeds 8 GB.
Does T Search support vision tasks?
No. The model has no vision capabilities.
What is the maximum context length for T Search?
The trained context length is 262144 tokens.