Sign in

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

Hy-Memory-30B-A3B vs Qwen3-VL-32B-Instruct

Hy-Memory-30B-A3B scores 61 (C) on agent readiness against Qwen3-VL-32B-Instruct's 56.4 (C), and leads in 3 of 4 scored categories. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 4969 open weights comparisons

Hy-Memory-30B-A3BTencent (Hy team) · Open-weight model C61/100#62 of 135 open-weight models Qwen3-VL-32B-InstructAlibaba (Qwen team) · Open-weight model C56.4/100#97 of 135 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

Ahead on

  • Risk, 60 against 55
  • Agent interface, 65 against 60
  • Documentation and upkeep, 68 against 31

Watch for

Not a general assistant or a tool caller

Qwen3-VL-32B-Instruct C

Best for An agent with a 32 GB GPU or more that wants the largest dense Qwen3-VL model for images, documents and video

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

Watch for

No safety evaluation, agent-use guidance or security contact

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.

Documentation and upkeep Hy-Memory-30B-A3B +37

Hy-Memory-30B-A3B 68

Model card 8, Intended use (the write path of Mem0, MemOS and Hy-Memory), parameters (30B, about 3B active) and languages (English and Chinese, in the metadata) are there. Training data 5, A general description of the two training stages inside the harnesses, with no datasets, sizes or cut-off. Last change 20, the last commit, on 16 October 2026, added the licence and the card, 25 days before this check. Responsiveness 20, Of the 4 discussions that aren't pull requests (16 to 30 October 2026), 3 have a reply from a tencent organisation member. Version policy 5, A first release, with nothing replaced. File health 10, Config, tokenizer and template agree on the architecture, the context and the thinking levels. 8 + 5 + 20 + 20 + 5 + 10 = 68.

Qwen3-VL-32B-Instruct 31

The card misses limitations, languages and a cut-off (11). Training data is described only in the technical report, with no cut-off (5). The last change to code that runs it was the qwen-vl-utils fix of 4 January 2026, and the weights haven't changed since November 2025; the Hub commits for all three repositories and the QwenLM/Qwen3-VL head (30 January 2026) were the same on 4 November (5). Jie Huang, a Qwen organisation member, a named author of the Qwen3-VL Technical Report and the author of nine commits in QwenLM/Qwen3-VL, answered two of the 11 Hugging Face discussions that aren't pull requests, both on 27 October 2025; no publisher reply since, and GitHub issues weren't counted (5). The FP8 build's files were replaced in place the day after release with no note, after it had shipped the Thinking edition's files for three days (0). The GGUF card's example names a file the repository doesn't hold (5). 11+5+5+5+0+5 = 31.

Risk Hy-Memory-30B-A3B +5

Hy-Memory-30B-A3B 60

File safety 25, 51 safetensors shards and no pickle or Python files. Provenance 15, files in the tencent organisation that the card's own resource list links to (10), with a SHA-256 listed for all 53 large files (5). Safety evaluation 0, no safety results on the card. Agent guidance 0, no prompt-injection guidance, instruction hierarchy, account of trained refusals or general cautions on the card. Licence risk 15, Apache 2.0 with no use policy, no field-of-use limit, no threshold and no clause letting Tencent change the terms. Security programme 5, Tencent's Security Response Center takes vulnerability reports company-wide with published reward rules, as the Hy3 listing records (5). 25 + 15 + 0 + 0 + 15 + 5 = 60.

Qwen3-VL-32B-Instruct 55

Safetensors and GGUF only and no code in the repositories, so the FP8 card's trust_remote_code flag runs nothing (25). Files in the Qwen organisation with a checksum on every file (15). No safety evaluation at all (0). No guidance for agent use, which matters for a model sold as a GUI agent (0). Apache 2.0 carries none of the licence risks (15). No security contact, disclosure policy or public advisories found for Qwen (0), and Alibaba's group-wide security centre wasn't checked. 25+15+0+0+15+0 = 55.

Agent interface Hy-Memory-30B-A3B +5

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.

Qwen3-VL-32B-Instruct 60

A Jinja chat template in the repository (20). The tool-call format lives only in the template, Hermes-style JSON in tool_call tags, and Alibaba names no parser (10). Trained for function calling with several calls allowed in a turn, per the family's technical report (20). No documented structured output (0). No thinking mode in this edition, so reasoning control scores 0 by the rule. 262,144 tokens of native context (10). 20+10+20+0+0+10 = 60.

Score by category

CategoryWeight this runHy-Memory-30B-A3BQwen3-VL-32B-InstructEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%258585even
Risk20%206055Hy-Memory-30B-A3B +5
Agent interface10%106560Hy-Memory-30B-A3B +5
Documentation and upkeep10%106831Hy-Memory-30B-A3B +37
Negative events≤1500
TotalC 61/100C 56.4/100

Facts side by side

FactHy-Memory-30B-A3BQwen3-VL-32B-Instruct
KindOpen-weight modelOpen-weight model
VendorTencent (Hy team)Alibaba (Qwen team)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-10-162025-11-01
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone2.5/5 (4)

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.

Qwen3-VL-32B-Instruct

Qwen3-VL-32B-Instruct is the largest dense Qwen3-VL model, for screenshots, documents, charts and video. Alibaba's Q4_K_M GGUF with its vision file needs about 25 GB, and Transformers, vLLM, SGLang, llama.cpp and Ollama run it under plain Apache 2.0. It has no thinking mode or published safety work, and only one provider was found serving it.

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

Qwen3-VL-32B-Instruct

  1. Start it with llama-server -hf Qwen/Qwen3-VL-32B-Instruct-GGUF:Q4_K_M --jinja -c 32768, or ollama run qwen3-vl:32b-instruct
  2. In Ollama the plain qwen3-vl:32b tag is the Thinking edition, so name 32b-instruct
  3. With the GGUF, load the mmproj vision file too, or images won't be read
  4. Parse tool calls as JSON inside <tool_call> tags, or use SGLang's --tool-call-parser qwen
  5. Use the card's sampling, temperature=0.7, top_p=0.8, top_k=20, presence_penalty=1.5 for vision and temperature=1.0, top_p=1.0, top_k=40, presence_penalty=2.0 for text
  6. Validate JSON output yourself, since structured output isn't documented
  7. vLLM needs 0.11.0 or later and Transformers 4.57.0 or later
  8. If you pulled the FP8 build before 22 October 2025, pull it again, since the earlier files were the Thinking edition's

Questions

Which is better for AI agents, Hy-Memory-30B-A3B or Qwen3-VL-32B-Instruct?

Hy-Memory-30B-A3B scores 61 (C) on agent readiness against Qwen3-VL-32B-Instruct's 56.4 (C), and leads in 3 of 4 scored categories.

Other comparisons with Hy-Memory-30B-A3B or Qwen3-VL-32B-Instruct

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