Sign in

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

Hy-Memory-30B-A3B vs Nanbeige4.3-33B

Hy-Memory-30B-A3B and Nanbeige4.3-33B score within a point of each other on agent readiness, 61 (C) and 60.8 (C). Nanbeige4.3-33B leads on agent interface. 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 Nanbeige4.3-33BNanbeige LLM Lab (BOSS Zhipin) · Open-weight model C60.8/100#71 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

  • Reach, 85 against 80
  • Documentation and upkeep, 68 against 56

Watch for

Not a general assistant or a tool caller

Nanbeige4.3-33B C

Best for Agents with a 32 GB GPU (INT4) or more, or the 128 GB reference machine at BF16, that want an Apache-tagged 33B model for long coding and tool loops.

Ahead on

  • Agent interface, 85 against 65

Watch for

Independent results so far are Artificial Analysis's alone (Intelligence Index v5.0 20.4, Terminal-Bench 4.0 29.8 per cent); the card's other agentic numbers are Nanbeige's own runs

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 Nanbeige4.3-33B +20

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.

Nanbeige4.3-33B 85

The chat template earns 20, Jinja in tokenizer_config.json. The tool-calling format earns 25, with the XML call format in the template and the qwen3_coder parser named for vLLM and SGLang. Trained tool calling earns 20, several calls per turn in the template. Structured output earns 0, as nothing mentions it. Reasoning control earns 10, thinking switched per request with the qwen3 reasoning parser named. Context earns 10 for 512K set in the config with no scaling.

Documentation and upkeep Hy-Memory-30B-A3B +12

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.

Nanbeige4.3-33B 56

The model card earns 11, with intended use, parameters, context and languages but no limitations, architecture or cut-off. Training data earns 0, as nothing describes it. Last change earns 20 for the quantised builds of 31 October 2026. Responsiveness earns 10, a Nanbeige member answering nine of 30 discussions. Version policy earns 5 for a first release, with a config change made and reverted under bare commit titles. File health earns 10, the files and the card agreeing.

Reach Hy-Memory-30B-A3B +5

Hy-Memory-30B-A3B 85

Memory 25, Tencent's own Q4_K_M GGUF is 18.24 GB, and 18.24 GB × 1.2 = 21.9 GB, which fits 24 GB but not 16 GB. Its Q3_K_M file and the two files with experts at 1 or 2 bits are below 4-bit precision and don't count. Runtimes 20, hy_v3 model code in released vLLM (HYV3ForCausalLM in the v0.33.0 registry), SGLang v0.5.23 (hunyuan_v3.py), Transformers v5.22.2 and llama.cpp b12242, 5 each. Builds 15, Tencent publishes an FP8 repository and a GGUF repository with Q4_K_M, Q6_K and Q8_0 files in its own organisation, so quantised builds at two precisions or more. Terms 15, Apache 2.0, with only a preamble naming Tencent as copyright holder above the licence text. Download 10, gated is false for the main, FP8 and GGUF repositories on 10 November 2026, so the files download with no account or terms to accept. Hosted 0, Hugging Face lists no inference provider for the model (an empty provider mapping on 10 November 2026), and the card names no API. 25 + 20 + 15 + 15 + 10 + 0 = 85.

Nanbeige4.3-33B 80

Memory earns 20, since Nanbeige's INT4 build is 22.57 GB, about 27 GB with a fifth added, which fits 32 GB. Runtimes earn 20 from released vLLM, SGLang, Transformers and llama.cpp, which all run the Llama architecture, and Ollama and LM Studio have no build. Builds earn 15 for Nanbeige's INT4, INT8 and FP8 builds of 31 October 2026. Terms earn 15 for Apache 2.0 with nothing added, though only the metadata names it. Download earns 10, with no gate. Hosted earns 0, as no provider or Nanbeige API serves it.

Score by category

CategoryWeight this runHy-Memory-30B-A3BNanbeige4.3-33BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%258580Hy-Memory-30B-A3B +5
Risk20%206060even
Agent interface10%106585Nanbeige4.3-33B +20
Documentation and upkeep10%106856Hy-Memory-30B-A3B +12
Negative events≤1500
TotalC 61/100C 60.8/100

Facts side by side

FactHy-Memory-30B-A3BNanbeige4.3-33B
KindOpen-weight modelOpen-weight model
VendorTencent (Hy team)Nanbeige LLM Lab (BOSS Zhipin)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0 (Hub metadata only; the repository has no LICENSE file)
Read-only variant documentednono
llms.txtnono
Last release2026-10-162026-10-31
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked

How the scores have moved

Hy-Memory-30B-A3B

No score change since it was listed.

Nanbeige4.3-33B

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.

Nanbeige4.3-33B

A dense 33B Llama-architecture cousin for long agentic coding and office tasks, with per-request thinking, XML tool calls that stock vLLM and SGLang parse, and 512K of context. Nanbeige's INT4 build needs about 27 GB. Artificial Analysis's first independent runs give it 20.4 on its Intelligence Index, and there are no safety results, training data notes or licence file.

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

Nanbeige4.3-33B

  1. Serve with vllm serve Nanbeige/Nanbeige4.3-33B --enable-auto-tool-choice --reasoning-parser qwen3 --tool-call-parser qwen3_coder, as the card says, or SGLang with the same two parsers
  2. On a 32 GB GPU use Nanbeige/Nanbeige4.3-33B-INT4 with the same vLLM or SGLang flags; the INT8 and FP8 builds need about 43 GB
  3. Keep tool_call_format at its default xml, since qwen3_coder parses that format; the json option writes Hermes-style JSON calls, which need a different parser such as vLLM's hermes
  4. Pass chat_template_kwargs {"preserve_thinking": true} for multi-turn tool use and coding, and {"enable_thinking": false} to skip reasoning, as the card recommends
  5. Use temperature 1.0, top_p 0.95 and up to 65,536 new tokens for agent work, and temperature 0.6 for reasoning and chat, per the card
  6. Send your own system prompt, since without one the template injects a Chinese identity line, or a Chinese tool-expert prompt when tools are passed
  7. Send one system message at the start only, as the template raises an error for a later one
  8. In plain Transformers pass use_cache=True to generate, since config.json and generation_config.json set it false; trust_remote_code isn't needed

Questions

Which is better for AI agents, Hy-Memory-30B-A3B or Nanbeige4.3-33B?

Hy-Memory-30B-A3B and Nanbeige4.3-33B score within a point of each other on agent readiness, 61 (C) and 60.8 (C). Nanbeige4.3-33B leads on agent interface.

Other comparisons with Hy-Memory-30B-A3B or Nanbeige4.3-33B

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