Tencent Hy3 Preview 295B
By Tencent · China
Updated 2026-07-13
Overview
Tencent's frontier preview: 295B MoE with 21B active params plus a 3.8B MTP module, 80 layers, top-8 of 192 experts, with fused fast/slow thinking. Released April 2026 under the custom Hunyuan license.
When to pick this model
- Research on fused fast/slow-thinking architectures
- Long-context workloads up to 256k tokens
- Base or Instruct fine-tuning at frontier scale
- Deployments where Tencent's Hunyuan license is acceptable
- Comparing Chinese hyperscaler frontier weights
VRAM requirements by quantization
| Quantization | VRAM required |
|---|---|
| Q4_K_M (recommended) | 177 GB |
| Q5_K_M | 210 GB |
| Q8_0 | 315 GB |
| FP16 (no quantization) | 590 GB |
VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.
In practice, Tencent Hy3 Preview 295B is server-class even at Q4_K_M (177 GB). Stepping up to Q8_0 nearly doubles the footprint to 315 GB, and unquantized FP16 weights take 590 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.
Without a GPU, Tencent Hy3 Preview 295B needs roughly 200 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 2 tokens/sec on entry-level GPUs, on the order of 8 tokens/sec on a mid-range card, and up to 25 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.
What hardware do you need
The table below matches Tencent Hy3 Preview 295B to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.
| GPU memory | Example cards | Best fit for Tencent Hy3 Preview 295B |
|---|---|---|
| 8 GB | RTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GB | Does not fit — needs 177 GB at Q4_K_M |
| 12 GB | RTX 5070, RTX 5070 Ti Laptop, RTX 4080 Laptop | Does not fit — needs 177 GB at Q4_K_M |
| 16 GB | RTX 5080, RTX 4080 Super, Radeon RX 9070 XT | Does not fit — needs 177 GB at Q4_K_M |
| 24 GB | RTX 4090, Radeon RX 7900 XTX, RTX 5090 Laptop | Does not fit — needs 177 GB at Q4_K_M |
| 32 GB | RTX 5090 | Does not fit — needs 177 GB at Q4_K_M |
Which GPU should you buy to run Tencent Hy3 Preview 295B?
To run Tencent Hy3 Preview 295B locally at Q4, you need ~177 GB of VRAM. The best value for this is a Apple Mac Studio (64+ GB unified memory).
As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.
Strengths
- Tencent's first frontier-scale open-weight release
- 256k context window
- Both Base and Instruct variants shipped
- MTP module accelerates long-form generation
- Fused fast/slow thinking in one model
Limitations
- Custom Tencent Hunyuan Community License — legal review required
- Around 177 GB VRAM in Q4
- No Ollama support at launch
- Preview status means rough edges in tooling
Typical workloads
In our catalog grid, Tencent Hy3 Preview 295B is filed under CN Frontier Reasoning, Long Context — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: multi-step reasoning and math-flavoured tasks.
The 250k-token context window is large enough to hold entire codebases' worth of files or long reports in a single prompt, which is what makes local RAG and document analysis practical. It ships under the Tencent Hunyuan License license — commercial use is generally possible but read the specific terms before embedding it in a product.
Architecture & training
Architecture: MoE 295B/21B active · 80 layers + 1 MTP layer · 192 experts top-8 · GQA 64Q/8KV · BF16
Training: Fused fast/slow-thinking.
A serious frontier preview from Tencent, held back from broader adoption by its custom license.
Quick start
# HuggingFace : tencent/Hy3-previewOr use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.
Similar models worth comparing
Frequently asked questions
How much VRAM does Tencent Hy3 Preview 295B need?
At the recommended Q4_K_M quantization, Tencent Hy3 Preview 295B needs about 177 GB of VRAM. Q8_0 takes 315 GB, and unquantized FP16 weights take 590 GB.
Can Tencent Hy3 Preview 295B run without a GPU?
Yes — with roughly 200 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.
What context window does Tencent Hy3 Preview 295B support?
Tencent Hy3 Preview 295B supports a 250k-token context window (256,000 tokens).
Can I use Tencent Hy3 Preview 295B commercially?
Tencent Hy3 Preview 295B ships under the Tencent Hunyuan License license. Commercial use is generally permitted subject to its terms — review the license text before shipping a product.
How fast is Tencent Hy3 Preview 295B on consumer hardware?
Our compatibility engine estimates on the order of 8 tokens/sec on a mid-range GPU and up to 25 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.
Which quantization of Tencent Hy3 Preview 295B should I download first?
Start with Q4_K_M (177 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. It does not fit a single 24 GB consumer card — plan for multi-GPU or server hardware.