T Search — Hardware Requirements & GPU Compatibility
ChatFunctions
T Search is a 36.0B-parameter open language model from t-tech. It supports a context window of up to 262,144 tokens. At BF16 it needs about 72.29 GB of VRAM — see which GPUs and Macs can run it below.
107 downloads
29 likesSpecifications
- Publisher
- t-tech
- Parameters
- 36.0B
- Architecture
- Qwen3_5MoeForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,320
- Release Date
- 2026-07-13
- License
- Apache 2.0
Get Started
HuggingFace
How Much VRAM Does T Search Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| BF16est. | 16.00 | 72.3 GB | 82.9 GB | 71.90 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run T Search?
BF16 · 72.3 GBT Search (BF16) requires 72.3 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 94+ GB is recommended. Using the full 262K context window can add up to 10.6 GB, bringing total usage to 82.9 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run T Search?
BF16 · 72.3 GB18 devices with unified memory can run T Search, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB).
Runs great
— Plenty of headroom
Decent
— Enough memory, may be tightWhere to Download T Search
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does T Search need?
T Search requires 72.3 GB of VRAM at BF16. Full 262K context adds up to 10.6 GB (82.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 36.0B × 16 bits ÷ 8 = 71.9 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 11 GB (at full 262K context)
VRAM usage by quantization
BF1672.3 GBBF16 + full context82.9 GB- Can NVIDIA GeForce RTX 5090 run T Search?
No — T Search requires at least 72.3 GB at BF16, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
- Can I run T Search on a Mac?
T Search requires at least 72.3 GB at BF16, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run T Search locally?
Yes — T Search can run locally on consumer hardware. At BF16 quantization it needs 72.3 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is T Search?
At BF16, T Search can reach ~61 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 72.3 × 0.65 = ~72 tok/s
Estimated speed at BF16 (72.3 GB)
~72 tok/s~72 tok/s~61 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of T Search?
At BF16, the download is about 71.90 GB.
- Which GPUs can run T Search?
No single consumer GPU has enough VRAM to run T Search at BF16 (72.3 GB). Multi-GPU or professional hardware is required.
- Which devices can run T Search?
19 devices with unified memory can run T Search at BF16 (72.3 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.