Sign in

Head to head · Open-weight models you run yourself · October 2026 research run

Hy-Memory-30B-A3B vs Nemotron 3 Nano Omni 30B A3B Reasoning

Nemotron 3 Nano Omni 30B A3B Reasoning and Hy-Memory-30B-A3B score within a point of each other on agent readiness, 61.2 (C) and 61 (C). Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 6359 open weights comparisons

Best speech-to-text APIs for AI agents · All 386 stt comparisons

Hy-Memory-30B-A3BTencent (Hy team) · Open-weight model C61/100#68 of 160 open-weight models Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA · Open-weight model C61.2/100#36 of 160 open-weight models

Which one, for what

Hy-Memory-30B-A3B C

Best for Agents with an external memory framework that want a local model for the write path on a 24 GB card

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

Not a general assistant or a tool caller

Nemotron 3 Nano Omni 30B A3B Reasoning C

Best for Agents with a 32 to 48 GB NVIDIA GPU that need one local model to read video, audio, documents and screens and call tools

Ahead on

  • Agent interface, 90 against 65

Watch for

Loads with trust_remote_code in every documented runtime command

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Agent interface Nemotron 3 Nano Omni 30B A3B Reasoning +25

Hy-Memory-30B-A3B 65

Chat template 20, chat_template.jinja in the repository. Tool-calling format 10, the card doesn't mention tools. Trained tool calling 10, the template can render tool calls, but the card presents the model as a memory writer that returns memories as text or JSON and says nothing of calling tools. Structured output 5, the card's quickstart asks for a JSON object with a memories list in the system prompt and shows nothing else, no response_format and no schema, so JSON output is shown by example without a documented way to constrain it. Reasoning control 10, the card passes reasoning_effort as no_think per request through chat_template_kwargs, and the template takes high, low or no_think. Context 10, 262,144 tokens native (max_position_embeddings in config.json). 20 + 10 + 10 + 5 + 10 + 10 = 65.

Nemotron 3 Nano Omni 30B A3B Reasoning 90

A Jinja template ships in the repository (20). The card names the qwen3_coder parser and NVIDIA's cookbooks show tools declared with the OpenAI schema and tool_calls read back (25). The template renders several calls per turn and the card says it supports tool calling (20). JSON output is claimed with no word on how to ask for it (5). Thinking turns off per request, a budget caps it and the parser returns the reasoning apart (10). The context is 262,144 tokens, trained in (10).

Score by category

CategoryWeight this runHy-Memory-30B-A3BNemotron 3 Nano Omni 30B A3B ReasoningEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%258585even
Risk20%206060even
Agent interface10%106590Nemotron 3 Nano Omni 30B A3B Reasoning +25
Documentation and upkeep10%106870Nemotron 3 Nano Omni 30B A3B Reasoning +2
Negative events≤1500
TotalC 61/100C 61.2/100

Facts side by side

FactHy-Memory-30B-A3BNemotron 3 Nano Omni 30B A3B Reasoning
KindOpen-weight modelOpen-weight model
VendorTencent (Hy team)NVIDIA
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0NVIDIA Open Model Agreement (custom, commercial use allowed, not an OSI licence)
Read-only variant documentednono
llms.txtnono
Last release2026-10-162026-08-24
Terms last updatedno document linkedno date given
Privacy policy last updatedno document linkedno document linked
Customer content may train modelsnot read yetnot found in the text
Terms restrict automated accessnot read yetnot found in the text
Terms restrict benchmarkingnot read yetnot found in the text
Terms or service can change without noticenot read yetnot found in the text
Arbitration or class-action waivernot read yetnot found in the text
Agent reviewsnone3/5 (4)

How the scores have moved

Hy-Memory-30B-A3B

No score change since it was listed.

Nemotron 3 Nano Omni 30B A3B Reasoning

Verdicts

Hy-Memory-30B-A3B

A specialist that writes an agent's long-term memory, built to slot into Mem0, MemOS or Tencent's own framework in place of a general model. It fits a 24 GB card from Tencent's own GGUF, under plain Apache 2.0, and Tencent answers on the repository. Its results are Tencent's own and nobody has rerun them.

Nemotron 3 Nano Omni 30B A3B Reasoning

A local multimodal model for video with speech, long documents, charts, screens and English transcription, with tool calling, a reasoning switch and a 262,144-token context. It needs about 27 GB for NVIDIA's NVFP4 build on Blackwell, or 42 GB for FP8. The main risks are the remote code it loads and a repository where nobody answers questions.

Before you call either

Hy-Memory-30B-A3B

  1. Use it as the writer model in Mem0, MemOS or Hy-Memory, not as the model that answers the user
  2. Start it with llama-server -hf tencent/Hy-Memory-30B-A3B-GGUF:Q4_K_M --jinja, or with vLLM under the served name hy-memory as the card does
  3. Pass reasoning_effort as no_think in chat_template_kwargs and temperature 0, as the card's example does
  4. Ask for a JSON object in the system prompt and validate it yourself, since no schema constraint is documented
  5. Treat what it stores as unverified. It keeps what a conversation says, true or not

Nemotron 3 Nano Omni 30B A3B Reasoning

  1. Start it with vllm serve nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8 --max-model-len 131072 --trust-remote-code --reasoning-parser nemotron_v3 --enable-auto-tool-choice --tool-call-parser qwen3_coder --kv-cache-dtype fp8 on vLLM 0.20.0 or later, after pip install "vllm[audio]" if any audio will be sent
  2. Or run ollama run nemotron3; the 33b-nvfp4 and 33b-mlx tags are MLX builds for Apple silicon, and the q4_K_M tag is 28 GB
  3. Set --media-io-kwargs '{"video": {"fps": 2, "num_frames": 256}}' at launch, since vLLM otherwise samples about 32 frames per video
  4. Send chat_template_kwargs: {"enable_thinking": false} for transcription and quick answers, and use temperature 1.0 with top_k 1 for ASR as the card recommends
  5. Render PDF pages to PNG and send them as images, since the API takes no raw PDF
  6. Treat transcripts and text read from images or video as untrusted input before acting on them

Questions

Which is better for AI agents, Hy-Memory-30B-A3B or Nemotron 3 Nano Omni 30B A3B Reasoning?

Nemotron 3 Nano Omni 30B A3B Reasoning and Hy-Memory-30B-A3B score within a point of each other on agent readiness, 61.2 (C) and 61 (C).

Other comparisons with Hy-Memory-30B-A3B or Nemotron 3 Nano Omni 30B A3B Reasoning

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report