Hy3 — Hardware Requirements & GPU Compatibility
ChatFunctions
Hy3 is Tencent's flagship Hunyuan 3 model, a mixture-of-experts design with roughly 299 billion total parameters and about 21 billion active per token. It combines fast and slow "thinking" modes in one architecture for reasoning, coding, and agent workloads. Only the active parameters compute per token, cutting cost versus a same-sized dense model, but all 299 billion weights must sit in memory, putting it in server-class territory; most people use a hosted endpoint, and local use needs multiple GPUs. The model supports a 262K token context window. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use. Published in July 2026, Hy3 is integrated across Tencent's products, including its CodeBuddy assistant.
Hy3 runs on a 192 GB+ Mac or a datacenter GPU
Best local pick → Mac Pro M2 Ultra (192 GB) · Q4_K_M · 182.3 GB · ~26 tok/s
Macs from 96 GB (IQ2_XXS · ~38 tok/s)
Apache 2.0
Not set up for it?
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Hy3
One recommended way. Every other method, OS and quant is in the step-by-step guide.
Recommended
ollama run hf.co/AngelSlim/Hy3-GGUF:Q4_K_MQ4_K_M runs on one B200 192 GB · 16K context
Download: Hy3-Q4_K_M.gguf182.33 GBAngelSlim
Other ways
each opens step-by-stepRun in cloud
Fits on B300 (288 GB) (105 GB headroom) · Q4_K_M
- Generation speed
- ~147 tok/s
- generation speed
- Cost per 1M output tokens
- $13.16
- per 1M output tokens
How Much VRAM Does Hy3 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | Runs on | |
|---|---|---|---|---|
| 127.6 GB | 132.7 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Runs on H200 NVL 141 GB | |
| 131.3 GB | 136.4 GB | 3-bit small — 3-bit small quantization | Runs on H200 NVL 141 GB | |
| 146.3 GB | 151.3 GB | 3-bit medium — 3-bit medium quantization | Runs on B200 192 GB | |
| 150.0 GB | 155.1 GB | 4-bit · legacy — 4-bit legacy quantization | Runs on B200 192 GB | |
| 179.9 GB | 184.9 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Runs on B200 192 GB | |
| 213.5 GB | 218.6 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Runs on Instinct MI325X 256 GB | |
| 247.1 GB | 252.2 GB | 6-bit, very good — 6-bit quantization, very good quality | Runs on Instinct MI325X 256 GB | |
| 299.4 GB | 304.5 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Runs on 5× H100 SXM 80 GB |
Selected Q4_K_M
4-bit medium quantization182.3GBat 16K context
- Weights
- 179.3 GB
- KV cache
- 2.7 GB
- Overhead
- 0.3 GB
Server-class: ~182.3 GB at 16K context · one B200 192 GB
Which Hardware Can Run Hy3?
Q4_K_M · 179.9 GBHy3 (Q4_K_M) requires 179.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 234+ GB is recommended. Using the full 262K context window can add up to 42.6 GB, bringing total usage to 222.5 GB. No consumer GPU has enough memory. 4 devices with unified memory can run Hy3, including Mac Studio (M3 Ultra, 512GB), Mac Studio (M3 Ultra, 256GB).
128–144 GB
Q4_K_M · best fit IQ3_XS (126.2 GB)
4 GPUs · 2 Mac classes
GH200 Grace Hopper Superchip~140Simulate output on GH200 Grace Hopper SuperchipH200 NVL~139Simulate output on H200 NVLH200 SXM~139Simulate output on H200 SXMM2 Ultra*128 GB~32Simulate output on Mac Pro M2 Ultra (128 GB)M5 Max128 GB~28Simulate output on Mac Studio M5 Max (128 GB)192+ GB
fits · 9.7 GB free · up to 64K ctx
6 GPUs · 1 Mac class · 2 device families
B200~147Simulate output on B200B300~147Simulate output on B300Instinct MI350X~54Simulate output on Instinct MI350XM3 Ultra*256–512 GB~26Simulate output on Mac Studio (M3 Ultra, 256GB)8x H100 SXM5~195Simulate output on NVIDIA DGX H1008x A100 SXM4~179Simulate output on NVIDIA DGX A100 640GB
By VRAM tier · typical GPUs and Macs at Q4_K_M
Consumer GPUs (up to 32 GB) and Macs up to 64 GB: too small for this model (needs ≥ 85.2 GB)8 GB tier →12 GB tier →16 GB tier →24 GB tier →Macs →
How good is Hy3?
llmrun Score blends public benchmark boards into one number; 100 = the average open model.
Not enough data yet for an llmrun Score.
A Score needs results on enough independent boards. How the Composite Score is built
Benchmarks
Here are all 2 boards that have results for this model, sorted by their weight in the llmrun Score; badges show who ran the test.
- LMArena Text
LMArena · Oct 2026Arena
Arena1453.2
#13/187 open
- LMArena WebDev
LMArena · Oct 2026Arena
Arena1505.9
#16/52 open
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| GLM 5.3 FlashZ.ai | 124.2 | 205.2 GB | —needs > 24 GB | same size |
| IQuest Q1IQuestLab | — | 195.4 GB | —needs > 24 GB | same size |
| MiMo V2.6 Flash MOPDXiaomi | — | 186.5 GB | —needs > 24 GB | same size |
| DeepSeek V4 Flash Vision ExpDeepSeek | — | 183.3 GB | —needs > 24 GB | same size |
| Step3StepFun | — | 219.1 GB | —needs > 24 GB | same size |
| Motif 3Motif-Technologies | — | 632.8 GB | —needs > 24 GB | same size |
Fine-tunes & variants(2)
Specifications
- Publisher
- Tencent
- Family
- Hunyuan 3
- Parameters
- 298.8B
- Active parameters
- 21B per token
- Architecture
- HYV3ForCausalLM
- Context Length
- 262,144 tokens
- Vocabulary Size
- 120,832
- Release Date
- 2026-07-02
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Hy3 need?
Hy3 requires 179.9 GB of VRAM at Q4_K_M, or 598.2 GB at BF16. Full 262K context adds up to 42.6 GB (222.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 298.8B × 4.8 bits ÷ 8 = 179.3 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 43.2 GB (at full 262K context)
VRAM usage by quantization
Can NVIDIA GeForce RTX 5090 run Hy3?
No — Hy3 requires at least 82.8 GB at IQ2_XXS, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.
What's the best quantization for Hy3?
For Hy3, Q4_K_M (179.9 GB) offers the best balance of quality and VRAM usage. Q4_K_L (183.6 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 82.8 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Hy3 on a Mac?
Yes — Mac Studio (M3 Ultra, 96GB) and 20 other Macs can run Hy3, the smallest at IQ2_XXS. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 179.9 GB of usable unified memory (RAM minus macOS overhead), from Mac Pro M2 Ultra (192 GB).
Can I run Hy3 locally?
Yes — Hy3 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Hy3?
At Q4_K_M, Hy3 can reach ~54 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)
Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.
Example: NVIDIA B200 → 12.6 GB active ÷ (8000 × 0.65) = 2.42655 ms, plus 80 layers × 0.055 ms = 4.40000 ms, so 1000 ÷ 6.82655 ms = ~146 tok/s
Estimated speed at Q4_K_M (179.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Hy3?
At Q4_K_M, the download is about 179.27 GB. The full-precision BF16 version is 597.57 GB. The smallest option (IQ2_XXS) is 82.17 GB.
Which GPUs can run Hy3?
No single consumer GPU has enough VRAM to run Hy3 at Q4_K_M (179.9 GB). Multi-GPU or professional hardware is required.
Which devices can run Hy3?
4 devices with unified memory can run Hy3 at Q4_K_M (179.9 GB), including Mac Pro M2 Ultra (192 GB), Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M2 Ultra (192 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.