Hunyuan-7B-Instruct
Official · BF16 · safetensors
Runtime certified: Transformers
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
Hunyuan · General · Hunyuan 7B
Hunyuan 7B Instruct: Specs, GPU Requirements and License
Hunyuan 7B Instruct is a current General release in the Hunyuan family, certified from its immutable official source revision.
Territory Restricted
Compare this model
Total parameters7.5B
Active parametersDense model
Context window262,144 tokens
Release statusCurrent · Current
ArchitectureHunYuanDenseV1ForCausalLM
ModalitiesText
LicenseTencent Hunyuan Community License Agreement
Deployment stateDeployable with certified configuration
Commercial stateTerritory Restricted
Release date2025-07-30
Architecture, strengths and use cases
Hunyuan 7B Instruct is an official self-hostable Tencent release in the Hunyuan General track. It uses HunYuanDenseV1ForCausalLM, carries 7.5B, supports a verified context window of 262,144 tokens, and exposes only source-certified checkpoints and runtime combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
Hunyuan 7B Instruct uses HunYuanDenseV1ForCausalLM with 7.5B. The stored architecture profile records 32 layers, hidden width 4096, 32 attention heads and a 262,144 token context ceiling where the official configuration publishes those fields.
Verified HunYuanDenseV1ForCausalLM architecture
262,144 token certified context
Official BF16, Unknown checkpoint coverage
Private LLM inference
Agentic workflows
Long-context document processing
Certified checkpoints and quantizations
Only exact, source-certified variants attached to this release are shown.
Recommended hardware
Use only the listed transformers runtime configuration with the exact checkpoint precision. The recommendation engine checks weight memory, KV cache, runtime overhead, safety headroom, GPU architecture and topology before ranking rentable and reference hardware.
Territory Restricted
The official license excludes one or more territories. FusionPointAI requires a separate legal review and shows no commercial hosting offer.
License and self-hosting considerations
The full 7.5B resident weight set must fit across the selected GPUs. Context and concurrency add KV-cache memory; MoE active parameters do not replace resident-weight memory.
Hunyuan 7B Instruct is published under Tencent Hunyuan Community License Agreement. The release-scoped official license link and verification date are retained with the catalogue record.
Territory Restricted. The official license excludes one or more territories. FusionPointAI requires a separate legal review and shows no commercial hosting offer.
Alternatives and sibling variants
Hunyuan A13B Instruct, Hunyuan-A13B-Instruct-GPTQ-Int4, Hunyuan-A13B-Instruct-GGUF
Release timeline
tencent/hunyuan/hunyuan-7b-instruct
Source details
Source revision: c3d6fe63f721a29cdc57a67f1a04877691ebcc0fcbb8cd515230746b15475315
Frequently asked questions
How much VRAM does Hunyuan 7B Instruct require?
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible runtime configurations.
Which runtimes support Hunyuan 7B Instruct?
Certified upstream runtime evidence is available for transformers.
Can Hunyuan 7B Instruct be used commercially?
The stored commercial classification is Territory Restricted. Consult the official Tencent Hunyuan Community License Agreement terms for the final obligations.
Official references
Last verified: 2026-08-26