⌘K
← All AI Models

Can you run Tencent Hy4 (preview) locally?

Hunyuan family · Aug 2026 · 780B parameters · Hugging Face model card

Tencent Hy4 (preview) is an open-weight mixture-of-experts model (activating 8 of 256 experts per token, 779.96B total parameters, 1,048,576-token context, apache-2.0 license). Running it locally needs roughly 512 GB of memory at Q4-class quantization (calculated) - multi-GPU server or large-unified-memory territory. Measured local speeds: not yet published here; we list unknowns as unknowns.

Minimum: 512 GB+ memory (Q4-class, calculated)  ·  Recommended: 768 GB+ for comfortable context headroom (Q4-class, calculated)

Parameters (total)
780B
VRAM at Q4_K_M (4k ctx)
514.8 GB
Context window
1,048,576 tokens
Architecture source
HF config.json (verified)

How much VRAM does Tencent Hy4 (preview) need at each quantization?

Tencent Hy4 (preview) needs 514.8 GB of VRAM at Q4_K_M. The table below lists weights-only size and total VRAM including overhead for each common quantization level with 4k and 32k token contexts.

QuantizationBits / weightWeights onlyTotal + KV @4k ctxTotal + KV @32k ctx
Q4_K_M 4.8 468.0 GB 514.8 GB 514.8 GB
Q5_K_M 5.7 555.7 GB 611.3 GB 611.3 GB
Q6_K 6.6 643.5 GB 707.8 GB 707.8 GB
Q8_0 8.5 828.7 GB 911.6 GB 911.6 GB
FP16 16 1,559.9 GB 1,715.9 GB 1,715.9 GB

Method: weights = parameters × bits-per-weight (Q4_K_M ≈ 4.8, Q5_K_M ≈ 5.7, Q6_K ≈ 6.6, Q8_0 ≈ 8.5, FP16 = 16), plus 10% loading overhead, plus KV cache from the verified architecture config (not applicable to this architecture). Source: HF-verified 2026-09-12 run2 via api (safetensors + config.json: MoE 256 experts, ctx 1M); VRAM figures are documented calculations, not measurements

Which GPUs can run Tencent Hy4 (preview) locally?

At Q4_K_M with a 4k context, Tencent Hy4 (preview) needs 514.8 GB of VRAM. The lists below are computed live from our GPU database and grouped by how much headroom the card has. Disclosure: CompareAIHardware.com participates in the Amazon Associates program and earns from qualifying purchases through links on this page. Affiliate relationships do not influence our recommendations.

Needs 2+ GPUs to run Tencent Hy4 (preview)

One of these cards is too small on its own, but a pair (tensor or pipeline parallel, ~90% efficiency) covers the 514.8 GB requirement. See our multi-GPU guide for setup.

GPUVRAMBandwidthType
AMD Instinct MI355X 288 GB ×2 8000 GB/s Data Center GPU
NVIDIA B300 (Blackwell Ultra) 288 GB ×2 8000 GB/s Data Center GPU

Frequently asked questions