Hy3 VRAM Requirements

Hy3 at a glance

Made by

Tencent, China

Released

July 2, 2026

Parameters

298.8B, 20B active

Context window

256K tokens

License

Apache 2.0, commercial use allowed

Reads

Text only

Tool calling

Supported

Reasoning

Adjustable reasoning effort

On Hugging Face

981 likes, 690K downloads last month (opens in a new tab)

Runs with

vLLM, SGLang, llama.cpp (Ollama, LM Studio), MLX (Mac) · vLLM recipe (opens in a new tab)

Checked against

KV cache matches the GGUF header of bartowski/Hy3-GGUF (opens in a new tab) (what llama.cpp allocates), October 17, 2026

VRAM by precision and context length

Weights plus the KV cache of one request (BF16 cache), in GiB. Add 1 to 3 GiB for the inference engine itself.

Hy3 GGUF files

Exact size of each quantization in bartowski/Hy3-GGUF (opens in a new tab), and the smallest GPU that runs it with llama.cpp, Ollama or LM Studio and an 8K-token context.

Read every day from Hugging Face. Split files are added together; vision projectors are left out.

How many GPUs to run Hy3

Fewest GPUs that fit the weights plus one 8K-token request. Data-center GPUs use vLLM (90% of memory usable), the others llama.cpp. Several GPUs split the model with tensor or pipeline parallelism.

8-bit: FP8 with vLLM (INT8 on GPUs without FP8), Q8_0 with llama.cpp. 4-bit: AWQ / GPTQ with vLLM, Q4_K_M with llama.cpp, both counted at the Q4_K_M size.

Cheapest way to run Hy3 today

For each GPU: the fewest cards that fit Hy3 with one 8K-token request, the most faithful weight format at that count, and the cheapest on-demand price (2026-10-17).

On-demand prices from AWS, Google Cloud, Azure, RunPod, Vast.ai, Oracle Cloud, OVHcloud, Scaleway, Verda, Akash and UpCloud, checked every hour. Serving many users needs more KV cache, so more memory: size it in the calculator. Some links are affiliate links: StudioTV may earn a commission, at no extra cost to you.

AWS, Google Cloud and UpCloud prices: Spare Cores (opens in a new tab), CC BY-SA 4.0 (opens in a new tab), shared under the same license.

Or use Hy3 through an API

No GPU to rent: these providers serve Hy3 and bill per token. Speeds are measured by Hugging Face for one request.

Prices and speeds from Hugging Face Inference Providers (opens in a new tab), read every day (October 17, 2026). An API wins at low volume; renting GPUs wins when they stay busy: the calculator gives the break-even.

Recommended settings for Hy3

Sampling defaults from the official generation_config.json (opens in a new tab) of tencent/Hy3.

vLLM and SGLang apply these defaults unless a request sets its own. With llama.cpp, pass them yourself: --temp 0.9 --top-p 1

Reasoning. Adjustable reasoning effort. Reasoning tokens take context and KV cache like any other token: leave room for them.

KV cache: how memory grows with context

Architecture: 80 layers · 80 full attention (8 KV × 128). Every layer keeps keys and values for every token (grouped-query attention), so the cache grows linearly with context. Only 20B parameters are active per token, but all 299B must sit in memory: VRAM depends on the total, speed on the active part.

Hy3 VRAM badge

For a model card or a README: the 4-bit size and the smallest GPU it fits on, linked to this page. Data as JSON: /api/models/hy3.json.

[![Hy3 VRAM](https://studiotvai.com/badge/hy3.svg)](https://studiotvai.com/vram-requirements/hy3)

Other models

Same family (large moe): MiniMax M2.7 · DeepSeek R1 · Kimi K2.6 · GLM-5.3 · GLM-5.3-Flash · DeepSeek V4 Flash · DeepSeek V4 Pro · DeepSeek V4.1 Flash · MiMo-V2.6 Pro · MiMo-V2.6 Flash · Muse Spark Open · Kimi K3 · Mistral Large 4 · DeepSeek V4 Flash Vision Exp · Qwen3.8 2.4T-A95B · Ornith 1.5 397B · Atria Dawn Preview · Intern S2 397B · DeepSeek V3 · DeepSeek V3.1 · Kimi K2.7 Code · Kimi K2.5 · Kimi K2 · GLM-5.2 · GLM-5.1 · GLM-5 · MiniMax M2.5 · MiniMax M2 · MiMo-V2.5 · Ornith-1.0 397B · Qwen3 235B-A22B · Qwen3.5 397B-A17B · GLM-4.7 · GLM-4.5 · Ling-3.1-flash · Step 5 Preview

Estimates, not guarantees: computed from the official config.json with the same engine as the LLM VRAM Calculator. Real usage depends on your engine version and settings.