Lounge
Connecting…
Connecting…
View all

Tencent Hy4-flash: Specs, API Cost, and Local Setup

Tencent Hy4-flash is a 220B-total, 12B-active MoE model with 1M context. See API pricing, GGUF sizes, GPU needs, and the Tencent Hy License terms.

AILatest7 min read0 viewsPublished Updated
Contents8 sections
  1. What is Tencent Hy4-flash? Architecture and key specs
  2. How to read the official benchmark and cost claims
  3. Using Hy4-flash through an API
  4. Local hardware requirements
  5. Licensing: can you use it commercially?
  6. A practical checklist before you adopt it
  7. Frequently asked questions
  8. Sources and references

Key takeaways

  • Tencent Hy4-flash is an open-weight multimodal mixture-of-experts model: 220B total parameters, about 12B active per token, text and image input, and up to 1M tokens of context.
  • Its headline results (WorkIndex 42.1, blind-test satisfaction 2.79/4) come from Tencent's own benchmark and internal users, so treat them as claims to verify.
  • On OpenRouter, the Tencent Cloud provider lists $0.035 per million input tokens and $0.1405 per million output tokens as of November 20, 2026.
  • Running it locally is a big-iron job: the smallest official GGUF is 125.73 GiB, and llama.cpp support still lives in an unmerged pull request.
  • The Tencent Hy License is Apache 2.0-based but requires a separate agreement for model-as-a-service providers above $50M revenue or products above 100M monthly users.

Tencent Hy4-flash is an open-weight multimodal model from Tencent's Hy team (the group formerly branded Hunyuan). According to the official model card, it has 220B total parameters but activates only about 12B per token, takes text and images as input, produces text, and supports a context window of up to 1M tokens. As of November 20, 2026, the repository had 479 likes and was drawing a lot of attention on Hugging Face.

The short answer for most people: try it through an API first. Despite the "flash" name and the small active-parameter count, local inference starts at roughly 128GB of memory, and the tooling is still pre-release. If you plan to build a commercial product on it, read Section 10 of the license before anything else. Everything below is based on the model card, license, OpenRouter listing, GGUF repository, and vLLM recipe as checked on November 20, 2026.

What is Tencent Hy4-flash? Architecture and key specs

What is Tencent Hy4-flash? Architecture and key specs

Tencent calls Hy4-flash its most cost-effective Hy model to date. Three checkpoints were released together: the instruction-tuned Hy4 flash, an FP8-quantized Hy4 flash-FP8, and a pre-trained Hy4 flash-base. The base model is not a chat model, so pick the instruct or FP8 version for assistants and agents.

Total parameters

Official value
220B (incl. 64B Engram)
Why it matters
Drives download size and memory

Active per token

Official value
11.3B text + 0.43B vision
Why it matters
Closer to compute cost and speed

Backbone

Official value
42 layers: 1 dense + 41 MoE
Why it matters
16 of 512 routed experts + 1 shared per token

Context

Official value
1M (1,048,576 tokens)
Why it matters
Serving configs set a much smaller default

Modalities

Official value
Text + image in, text out
Why it matters
Video is off in the vLLM recipe defaults

Reasoning

Official value
reasoning_effort high (default) or no_think
Why it matters
no_think skips the thinking phase

Where the efficiency comes from

  • Hybrid attention. Sparse attention and sliding-window attention are interleaved 1:3. Tencent says this shrinks the KV cache to 1/24 of Hy3 and 1/6 of Hy4.
  • LatentMoE. Routed experts compute in a lower-dimensional latent space.
  • Engram n-gram embeddings. A 63.5B-parameter table of learned bigram and trigram representations, looked up by hashing. It inflates the parameter count, but vLLM offloads it to host RAM by default.

A built-in 0.85B drafter called DFly2 handles speculative decoding by reusing the main model's KV cache. Tencent reports decoding above 150 tokens per second when combining megakernels, 4-bit quantization, and DFly2 on its own serving stack. Do not expect that number on a workstation.

How to read the official benchmark and cost claims

Most of the headline numbers are Tencent-run evaluations. They are useful for direction, not as independent proof.

WorkIndex 42.1 (Hy4 preview 39.7, Hy4 51.4)

Basis
Internal benchmark, 8 task sets
Caveat
Built around WorkBuddy office tasks: slides, docs, spreadsheets

Cost per task 1/13 of Hy4 preview, 1/20 of Hy4

Basis
Same WorkIndex tasks
Caveat
The 1/8 vs DeepSeek-V4.1-Flash-1017 figure uses Max-tier, peak-hour pricing

Blind test 2.79/4 vs Claude Haiku 5.5 at 2.81/4

Basis
85 internal users, 259 tasks
Caveat
Median 6.7 minutes and RMB 0.26 per task

MMLU 88.7 and other base scores

Basis
Few-shot on the base model
Caveat
Tencent notes format failures may distort these scores

The pitch is "close to a small frontier model, for much less money," not "best model available." Tencent itself recommends Hy4-flash for deep search, document processing, slide creation, simple frontend demos, and computer use, and points people to the larger Hy4 for long-horizon software engineering. Because the blind testers were Tencent employees working on Tencent product tasks, rerun the comparison on your own prompts and check independent leaderboards before switching.

New open models trend and fade quickly. The theddari AI Telegram trends page shows which models developers keep talking about after launch day, which helps separate hype from sustained interest.

Using Hy4-flash through an API

Hosted: OpenRouter

The OpenRouter listing shows Tencent Cloud as the provider at $0.035 per million input tokens and $0.1405 per million output tokens as of November 20, 2026, with one additional price line on the full table. Call it with the model ID tencent/hy4-flash on the standard Chat Completions endpoint; it accepts tools, reasoning, response_format, and streaming.

  • A single provider means no failover if Tencent Cloud has an outage.
  • OpenRouter says the model is not available through EU in-region routing, which matters for teams with data-residency requirements.
  • Check the provider's own data retention and processing-location terms before sending customer data.

Self-hosted: vLLM or SGLang

Tencent recommends vLLM or SGLang for production. Both expose an OpenAI-compatible /v1 endpoint. The model card suggests temperature 0.9 and top_p 1.0, and passing reasoning_effort: no_think through chat template kwargs for direct replies. The vLLM recipe notes that no released vLLM wheel supports the architecture yet, so you need the dedicated vllm/vllm-openai:hy4-flash Docker image. Transformers support likewise requires installing from a specific pull-request commit.

Local hardware requirements

Local hardware requirements

Twelve billion active parameters does not mean it runs like a 12B model. A mixture-of-experts model only computes with a few experts per token, but every expert's weights still have to sit in memory. Plan around the 220B total.

vLLM BF16

Size (official)
440.5 GB download, 529 GB VRAM hint
Notes
8-way tensor parallel on H100/H200/B200-class GPUs

vLLM FP8

Size (official)
287.1 GB download, 345 GB VRAM hint
Notes
Hopper or Blackwell data-center GPUs

GGUF Q4_K_M

Size (official)
156.79 GiB
Notes
Standard 4-bit, the default pick

GGUF Q3_K

Size (official)
144.70 GiB
Notes
Mixed Q3/Q4 experts

GGUF IQ2-AH

Size (official)
125.73 GiB
Notes
Smallest of the five builds

The vLLM VRAM hints are simply download size times 1.2, a conservative estimate; offloading the Engram table to CPU memory lowers real GPU usage but raises your host-RAM needs. AMD Instinct is not supported yet, and data parallelism, pipeline parallelism, and LoRA serving are listed as unsupported. The recipe starts with an 8,192-token context and four concurrent sequences, so using anything near 1M tokens needs far more memory.

GGUF on a workstation

Tencent's AngelSlim team published Hy4-flash-GGUF with five builds. On a Mac M5 Max with 128GB, they report about 48 tokens per second of decoding for Q4_K_M at 4K context, measured on WorkBuddy tasks. Since that file is larger than 128GB, follow their Mac-specific README rather than default settings. llama.cpp support is in PR #32517, which was not merged at the time of checking, so you must build that branch yourself. The main model card describes the GGUF as provided for end-to-end testing. One-click Ollama or LM Studio links may appear on the page but can fail until an official llama.cpp release adds the architecture.

Licensing: can you use it commercially?

Hy4-flash ships under the Tencent Hy License 1.0. It is derived from Apache 2.0 but is not Apache 2.0. The grant is worldwide and royalty-free, and the key difference is Section 10, which adds commercial terms for large model-as-a-service businesses.

  1. 1

    Are you a MaaS provider?

    MaaS means giving third parties remote access to model inference or fine-tuning, for example through an API, where they submit their own inputs, parameters, or training data. End-user products with model capabilities confined to specific features, and services that just relay requests to an independent third-party model service, are excluded.

  2. 2

    Check the size thresholds

    A MaaS business needs a separate written license from Tencent if its worldwide gross revenue exceeded $50 million in any consecutive 12-month period (from any source, not just this model), or before using the model in a product with more than 100 million monthly active users.

  3. 3

    Check the internal-use exception

    Purely internal use is exempt, as long as neither the model, derivatives, nor their outputs are made available to third parties.

  4. 4

    Check redistribution rules

    Fine-tuned, quantized, distilled, merged, or pruned weights count as derivative works. Redistribution must include the license and change notices, and you cannot add terms that remove or limit Section 10.

For most startups and internal tools, that means you can proceed. Large companies selling general-purpose model access are the main group that needs to contact Tencent at [email protected].

A practical checklist before you adopt it

  1. Match the task. Everyday document, search, and slide work fits Tencent's own recommendation; long agentic coding sessions are where Tencent points to Hy4 instead.
  2. Pilot via API. Run 20 to 30 of your real prompts on OpenRouter, logging quality, latency, and token use in both high and no_think modes.
  3. Look for independent evaluations. Weigh third-party leaderboards and community tests alongside Tencent's internal numbers.
  4. Map the data path. For hosted use, confirm provider location and logging. For self-hosting, confirm GPU type, host RAM, and framework versions.
  5. Document the license call. Write down whether you expose general-purpose model access and whether you cross the revenue or user thresholds.
  6. Pin versions. The llama.cpp branch, Transformers commit, and Docker image are all pre-release, so record exactly what you deployed.

Tencent Hy4-flash makes a clear bet on cheap, good-enough performance: 220B total parameters, about 12B active, 1M context, and very low hosted pricing. The trade-offs are that its strongest evidence is self-reported, local tooling is still unmerged, and large MaaS operators face extra licensing terms. Start small through an API, verify quality on your own work, and confirm the license position before scaling up.

Frequently asked questions

Is Hy4-flash free for commercial use?
Mostly, with one carve-out. The Tencent Hy License 1.0 grants a worldwide, royalty-free license, but Section 10 says a model-as-a-service (MaaS) business needs a separate written license if its worldwide gross revenue exceeded $50 million in any 12-month period, or if it uses the model in a product with more than 100 million monthly active users. Feature-limited end-user apps, simple relays to a third-party model service, and purely internal use with no outputs shared externally are outside that requirement. Get legal review if your product exposes general-purpose model access.
Can I run Hy4-flash on a Mac or a single gaming GPU?
Not on typical consumer hardware. The official GGUF builds range from 125.73 GiB (IQ2-AH) to 156.79 GiB (Q4_K_M). The GGUF repo publishes tests on a 128GB Mac M5 Max and a 128GB RTX Spark using dedicated setup guides, and you must build llama.cpp from unmerged PR #32517. A 24GB graphics card cannot hold the weights.
How is Hy4-flash different from Hy4?
Hy4-flash is the cheaper sibling. Tencent says hybrid attention, LatentMoE, and Engram n-gram embeddings cut its KV cache to one-sixth of Hy4's. On Tencent's internal WorkIndex, Hy4-flash scores 42.1 versus 51.4 for Hy4, at about one-twentieth of the average cost per task. Tencent recommends Hy4 for long-horizon software engineering and Hy4-flash for everyday productivity work.
Does Hy4-flash use an OpenAI-compatible API?
Yes, in both common setups. OpenRouter exposes it as tencent/hy4-flash through its Chat Completions endpoint, and self-hosted vLLM or SGLang servers expose an OpenAI-compatible /v1 endpoint. Reasoning is on by default (reasoning_effort high); pass no_think for direct answers.

Sources and references

  1. 1tencent/Hy4-flash model card (Hugging Face)(opens in a new tab)huggingface.co
  2. 2Tencent Hy License 1.0 full text (Hugging Face)(opens in a new tab)huggingface.co
  3. 3OpenRouter: Tencent Hy4 flash(opens in a new tab)openrouter.ai
  4. 4AngelSlim/Hy4-flash-GGUF model card(opens in a new tab)huggingface.co
  5. 5vLLM Recipes: tencent/Hy4-flash(opens in a new tab)recipes.vllm.ai