Hy4 preview
768.6B total, 47.8B active · 1024k context · Apache License 2.0 · released 2026-08-27
chatcodingagenticreasoning
In short
Hy4 preview is an open model from tencent with 768.6B parameters (47.8B active per token). At mlx-4bit, Hy4 preview needs about 405 GB of memory at 8k context and 416 GB at 128k, counting the weights, the KV cache and runtime buffers. Nothing we price in Canada runs Hy4 preview fully in memory at 128k context at a usable speed; see the table for what comes closest.
Updated . Speeds are estimates; how they are worked out.
Cheapest way to run it in Canada today
Nothing in stock in Canada today runs Hy4 preview fully in memory at 128k context at 15 tok/s or more. A shorter context needs less memory; the table below shows what comes closest.
What to run it on in Canada
Fully in memory at 128k context, priced at retailers today.
Nothing we price holds this model fully in memory.
All hardware that runs it
Everything we price, best value first. Two cards split the model by layers.
Nothing we price can run it at this context.
Memory needed
Weights, KV cache and runtime buffers at each context length (KV cache at fp16).
| Quant | File | @8k | @32k | @64k | @128k |
|---|---|---|---|---|---|
| mlx-4bitmlx | 403.6 GB | 405.0 GB | 407.2 GB | 410.2 GB | 416.0 GB |
Run it
Copy a command for the runtime you use.
- mlx-4bit
- LM Studio
lms get mlx-community/Hy4-preview-4bit - MLX
mlx_lm.server --model mlx-community/Hy4-preview-4bit
- LM Studio
Notes
Early preview release with known issues such as over-long reasoning and over-verification. Reasoning defaults to "high"; the card's deployment examples use the FP8 variant on 8 GPUs (tensor-parallel 8) with a dedicated vLLM/SGLang image. Sparse or compressed attention: KV read per token is estimated as full attention. Excludes 11.3B parameters of multi-token-prediction layers, which local runtimes do not load.
Questions
- How much VRAM does Hy4 preview need?
- At mlx-4bit, Hy4 preview needs about 405 GB of memory at 8k context and 416 GB at 128k, counting the weights, the KV cache and runtime buffers.
- Can I run Hy4 preview on a 16 GB GPU?
- No: it does not fit in 16 GB at 128k context, even with system RAM.
- Can I run Hy4 preview on a 24 GB GPU?
- No: it does not fit in 24 GB at 128k context, even with system RAM.
- What licence is Hy4 preview released under?
- Apache License 2.0, which allows commercial use.