**Hy-Memory-30B-A3B** is a compact long-term-memory writer model (~3B active parameters) developed by Tencent Hunyuan to execute the write path inside external memory frameworks. It directly replaces the general-purpose LLM inside **Mem0**, **MemOS**, and **Hy-Memory** (covering Chat, Working, and Coding scenarios), deciding what information to retain, how precisely to represent it, and how new evidence should update the persistent memory bank. The model is trained in two stages—Memory On-Policy Distillation (OPD) followed by Attributed Memory Reinforcement Learning—and transfers directly to unseen memory frameworks such as **EverMemOS**. Cross-harness macro-average scores on the fixed 20% benchmark matrix. Each harness score averages six metrics equally; Overall averages the four harnesses equally. EverMemOS is held out from training. Figure 1: Hy-Memory-30B-A3B is trained inside the same deployed harness configurations in both stages. OPD supplies dense teacher supervision on student-written state chains; RL examines the resulting banks, assigns chunk-level credit, and carries the selected bank across windows. In the rollout grid, each cell is the bank after chunk t of rollout i, shaded by its chunk score s_i[t]. Advantages are normalized within each column (dashed: one chunk-level group), so the best rollout can differ from chunk to chunk. The outlined cell is the final bank with the highest sum_t s_i[t], which becomes the parent of the next window.

Text generation

Input Text→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

Hy-Memory-30B-A3B-FP8

腾讯

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Text generation

Input Text→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

Hy-Memory-30B-A3B-GGUF

腾讯

This repository provides GGUF quantizations of Hy-Memory-30B-A3B for efficient local inference with llama.cpp. The releases use **Tencent Hunyuan's Hy-Memory quantization recipe**: imatrix calibration plus MoE-aware mixed precision. Routed experts, which dominate parameter count, can be compressed aggressively, while shared experts, attention, and input/output layers keep higher precision. On the same fixed Mem0 LoCoMo setup, even the **~8 GB** expert-mixed build stays within about **1.5 points** of the strongest Q6_K result (**57.25%** vs **58.78%**), so the quality drop remains small while the file size falls to roughly **one quarter** of Q8_0. All six files passed llama.cpp `--check-tensors`, real no-think generation, and the complete fixed 20% Mem0 LoCoMo evaluation. Each version builds its own memory bank under identical settings. These are single-run scores: they do not claim lossless quantization, and lower-bit variants are not guaranteed to beat higher-bit ones.

Text generation

Input Text→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

HY-Motion-1.0

腾讯

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Category pending

Input Not verified→ Output Not verified

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

HY-MT1.5-1.8B

腾讯

🤗  Hugging Face   |   🕹️  Demo      🤖  ModelScope   |   Hunyuan Translation Model Version 1.5 includes a 1.8B translation model, HY-MT1.5-1.8B, and a 7B translation model, HY-MT1.5-7B. Both models focus on supporting mutual translation across 33 languages and incorporating 5 ethnic and dialect variations. Among them, HY-MT1.5-7B is an upgraded version of our WMT25 championship model, optimized for explanatory translation and mixed-language scenarios, with newly added support for terminology intervention, contextual translation, and formatted translation. Despite having less than one-third the parameters of HY-MT1.5-7B, HY-MT1.5-1.8B delivers translation performance comparable to its larger counterpart, achieving both high speed and high quality. After quantization, the 1.8B model can be deployed on edge devices and support real-time translation scenarios, making it widely applicable. *!!! If you want to load fp8 model with transformers, you need to change the name"ignored_layers" in config.json to "ignore" and upgrade the compressed-tensors to compressed-tensors-0.11.0.*

Translation

Input Text→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

Hy-MT1.5-1.8B-1.25bit

腾讯

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Translation

Input Text→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

Hy-MT1.5-1.8B-1.25bit-GGUF

腾讯

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Translation

Input Text→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

Hy-MT1.5-1.8B-2bit

腾讯

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Translation

Input Text→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

Hy-MT1.5-1.8B-2bit-GGUF

腾讯

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Translation

Input Text→ Output Text

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

COST EXPLORER

Great models. Clear costs.

Cost analysis

Adjust monthly token usage to compare estimated API costs.

Monthly input tokens 10 MMonthly output tokens 2 M1 M = 1 million tokens · USD
Compares base text-token rates within the same channel

Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.

MODEL HANDBOOK

Understand before you choose

Selection guide & FAQ

How should API prices be compared?+

Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.

Do open weights mean free commercial use?+

Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.

Is the top-ranked model the best for me?+

Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.

Find your ideal AI model.

Explore AI models 84999

CHOCO-BRAIN-0.8B-v0.1

connectailab-CHOCO-BRAIN-v1

connectailab-rl-CHOCO-BRAIN_GUARD-v1-GGUF

Llama3.2-24B-A3B-II-Dark-Champion-INSTRUCT-Heretic-Abliterated-Uncensored-GGUF

Qwen3.8-27B-heretic-ara-NVFP4

SmolLM-135M-Instruct-GRPO

Qwen3.8-Flash-Next-Uncensored-Q4_K_M-Ngram-Q8_0

nyqo

HY-Embodied-0.5

Hy-Embodied-0.5-VLA-RoboTwin

Hy-Embodied-0.5-VLA-UMI

HY-Embodied-0.5-X

Hy-Embodied-RxBrain-1.0

Hy-Embodied-VLM-1.0

HY Image 3.5 Preview

Hy-Memory-30B-A3B

Hy-Memory-30B-A3B-FP8

Hy-Memory-30B-A3B-GGUF

HY-Motion-1.0

HY-MT1.5-1.8B

Hy-MT1.5-1.8B-1.25bit

Hy-MT1.5-1.8B-1.25bit-GGUF

Hy-MT1.5-1.8B-2bit

Hy-MT1.5-1.8B-2bit-GGUF

No matching models

Great models. Clear costs.

Understand before you choose

Follow trends. Find tools. Explore models.