Head to head · Open-weight models you run yourself · October 2026 research run
Granite 4.2 3B vs Hy-Memory-30B-A3B
Hy-Memory-30B-A3B scores 61 (C) on agent readiness against Granite 4.2 3B's 59.8 (C), and leads in 1 of 4 scored categories. Granite 4.2 3B leads on reach, agent interface and documentation and upkeep. 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
Which one, for what
Best for Agents on small hardware that want a permissive reasoning model for tool calls and coding, with thinking they can switch off
Ahead on
- Reach, 95 against 85
- Agent interface, 85 against 65
- Documentation and upkeep, 92 against 68
Watch for
No safety results published for 4.2, and only general safety cautions
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
Watch for
Not a general assistant or a tool caller
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 Granite 4.2 3B +24
Granite 4.2 3B 92
The card covers everything but a knowledge cut-off (17). IBM's disclosure lists the datasets with sources and sizes (20). The index file changed on 20 October 2026, 15 days before this check, and nothing in IBM's 4.2 repositories or the GitHub repository changed since (20). The two questions asked on IBM's 3B repositories have an IBM reply, and no new thread was opened after 21 October (20). Granite 4.1 3B stays in its own repository with no note (5), and the files agree with each other (10).
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.
Agent interface Granite 4.2 3B +20
Granite 4.2 3B 85
The template ships in the repository (20). The card shows how tools are declared and how calls come back, and names qwen3_coder for vLLM and SGLang (25). The template renders several calls in a turn (20). JSON output isn't documented for 4.2 (0). Thinking turns off or goes to low effort per request, with the reasoning returned apart in SGLang (10), and 131,072 tokens are native (10).
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.
Reach Granite 4.2 3B +10
Granite 4.2 3B 95
Memory earns the full 30, since IBM's 4-bit MLX build is 2.07 GB and Ollama's Q4_K_M build 2.2 GB, about 2.5 to 2.6 GB with the fifth added. Five named runtimes run the granite architecture in released versions or their own libraries, so runtimes take the cap of 25, though LM Studio has no 4.2 entry. IBM's FP8, FP4, GGUF and MLX builds earn 15. Apache 2.0 with nothing added gives terms 15 and the ungated repositories download 10. Hosted too is 0, since only DeepInfra serves it and watsonx.ai stops at 4.1.
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.
Risk Hy-Memory-30B-A3B +5
Granite 4.2 3B 55
File safety gets 15 of 25, safetensors only, less 10 because the card's vLLM command loads the repository's parser plugin. Provenance gets 15 for files in IBM's own organisation with hashes and a sigstore signature. Safety evaluation is 0, since 4.2 publishes no safety results. Agent guidance gets 5 for general cautions and the advice to add Granite Guardian. Apache 2.0 keeps licence risk at 15, and IBM's security.txt gives 5 of the security programme's 10.
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.
Score by category
| Category | Weight this run | Granite 4.2 3B | Hy-Memory-30B-A3B | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 95 | 85 | Granite 4.2 3B +10 |
| Risk | 20%20 | 55 | 60 | Hy-Memory-30B-A3B +5 |
| Agent interface | 10%10 | 85 | 65 | Granite 4.2 3B +20 |
| Documentation and upkeep | 10%10 | 92 | 68 | Granite 4.2 3B +24 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 59.8/100 | C 61/100 |
Facts side by side
| Fact | Granite 4.2 3B | Hy-Memory-30B-A3B |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | IBM | Tencent (Hy team) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-20 | 2026-10-16 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Agent reviews | 3.8/5 (4) | none |
Verdicts
Granite 4.2 3B
A small reasoning model for tool calls, coding and multilingual chat, published by IBM under plain Apache 2.0 with signed files and a dataset disclosure, and run by llama.cpp, Ollama, vLLM, SGLang and Transformers from a 2.2 GB Ollama build. Thinking turns off or shortens per request. It has no published safety results and no documented JSON mode.
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.
Before you call either
Granite 4.2 3B
- Start it with
ollama run granite4.2:3b; set options.num_ctx in the request, since Ollama's default context is short and the model takes up to 131,072 - With vLLM 0.32.0 or later, serve
ibm-granite/granite-4.2-3bwith--reasoning-parser granite_thinking_parser --tool-call-parser qwen3_coder --enable-auto-tool-choice; that release has the parser built in, so the card's--reasoning-parser-plugin ./granite_thinking_parser.pyisn't needed - With SGLang 0.5.18 or later,
--reasoning-parser auto --tool-call-parser autoresolve to IBM's recommended parsers, and the reasoning comes back in reasoning_content - Use temperature 1.0 and top_p 0.95 for every mode, as IBM requires
- Pass
enable_thinkingfalse for direct answers orlow_efforttrue for short reasoning, through chat_template_kwargs on an OpenAI-compatible server - Earlier turns' thinking is stripped by default (
truncate_history_thinking), so pass it false to keep reasoning in multi-turn history - For JSON, use the runtime's guided decoding, since IBM documents no JSON mode for 4.2
- Verify the files with
python -m model_signing verify sigstoreand IBM's identity, per IBM's signature guide
Hy-Memory-30B-A3B
- Use it as the writer model in Mem0, MemOS or Hy-Memory, not as the model that answers the user
- 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 - Pass
reasoning_effortas no_think inchat_template_kwargsand temperature 0, as the card's example does - Ask for a JSON object in the system prompt and validate it yourself, since no schema constraint is documented
- Treat what it stores as unverified. It keeps what a conversation says, true or not
Questions
Which is better for AI agents, Granite 4.2 3B or Hy-Memory-30B-A3B?
Hy-Memory-30B-A3B scores 61 (C) on agent readiness against Granite 4.2 3B's 59.8 (C), and leads in 1 of 4 scored categories. Granite 4.2 3B leads on reach, agent interface and documentation and upkeep.
Other comparisons with Granite 4.2 3B or Hy-Memory-30B-A3B
- Agents-A1-4B vs Granite 4.2 3B
- Agents-A1-4B vs Hy-Memory-30B-A3B
- Apertus v1.5 8B vs Granite 4.2 3B
- Apertus v1.5 8B vs Hy-Memory-30B-A3B
- Apodex-1.1-mini vs Granite 4.2 3B
- Apodex-1.1-mini vs Hy-Memory-30B-A3B
- Arete-27B vs Granite 4.2 3B
- Arete-27B vs Hy-Memory-30B-A3B
- BigBang-v1 vs Granite 4.2 3B
- BigBang-v1 vs Hy-Memory-30B-A3B
- Carbon-X vs Granite 4.2 3B
- Carbon-X vs Hy-Memory-30B-A3B
- Cosmos-Reason2-2B vs Granite 4.2 3B
- Cosmos-Reason2-2B vs Hy-Memory-30B-A3B
- Darwin-36B-Opus vs Granite 4.2 3B
- Darwin-36B-Opus vs Hy-Memory-30B-A3B
- DeepSeek-V3.2 vs Granite 4.2 3B
- DeepSeek-V3.2 vs Hy-Memory-30B-A3B
- DeepSeek V4.1 Flash vs Granite 4.2 3B
- DeepSeek V4.1 Flash vs Hy-Memory-30B-A3B
- DeepSeek-V4-Flash-0731 vs Granite 4.2 3B
- DeepSeek-V4-Flash-0731 vs Hy-Memory-30B-A3B
- DiffusionGemma 26B A4B IT vs Granite 4.2 3B
- DiffusionGemma 26B A4B IT vs Hy-Memory-30B-A3B
- Gemma 4 12B IT vs Granite 4.2 3B
- Gemma 4 12B IT vs Hy-Memory-30B-A3B
- Gemma 4 26B A4B IT vs Granite 4.2 3B
- Gemma 4 26B A4B IT vs Hy-Memory-30B-A3B
- Gemma 4 31B IT vs Granite 4.2 3B
- Gemma 4 31B IT vs Hy-Memory-30B-A3B
- Gemma 4 E2B IT vs Granite 4.2 3B
- Gemma 4 E2B IT vs Hy-Memory-30B-A3B
- Gemma 4 E4B IT vs Granite 4.2 3B
- Gemma 4 E4B IT vs Hy-Memory-30B-A3B
- GLM-4.5-Air vs Granite 4.2 3B
- GLM-4.5-Air vs Hy-Memory-30B-A3B
- GLM-4.7-Flash vs Granite 4.2 3B
- GLM-4.7-Flash vs Hy-Memory-30B-A3B
- GLM-5.3-Flash vs Granite 4.2 3B
- GLM-5.3-Flash vs Hy-Memory-30B-A3B
- GLM-5.3 vs Granite 4.2 3B
- GLM-5.3 vs Hy-Memory-30B-A3B
- gpt-oss-120b vs Granite 4.2 3B
- gpt-oss-120b vs Hy-Memory-30B-A3B
- gpt-oss-20b vs Granite 4.2 3B
- gpt-oss-20b vs Hy-Memory-30B-A3B
- Granite 4.2 30B vs Granite 4.2 3B
- Granite 4.2 30B vs Hy-Memory-30B-A3B
- Granite 4.2 3B vs Granite 4.2 8B
- Granite 4.2 3B vs Hy3
- Granite 4.2 3B vs Inkling
- Granite 4.2 3B vs Inkling-Small
- Granite 4.2 3B vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Granite 4.2 3B vs Kimi K3
- Granite 4.2 3B vs Kimi K3.1 Pro
- Granite 4.2 3B vs Kolibri-1
- Granite 4.2 3B vs Kronos
- Granite 4.2 3B vs Laguna M.1
- Granite 4.2 3B vs Laguna S 2.1
- Granite 4.2 3B vs Laguna XS 2.1
- Granite 4.2 3B vs LBS-27B
- Granite 4.2 3B vs LFM2.5-2.6B
- Granite 4.2 3B vs LFM3-1.7B
- Granite 4.2 3B vs LFM3-Audio-2B
- Granite 4.2 3B vs LFM3-Omni-2B
- Granite 4.2 3B vs LFM3-VL-2B
- Granite 4.2 3B vs Ling-3.0-tiny
- Granite 4.2 3B vs Ling-3.1-flash-1019
- Granite 4.2 3B vs MiMo-V2.6 Distill Qwen 9B
- Granite 4.2 3B vs MiniCPM-o 4.5
- Granite 4.2 3B vs MiniCPM-V 4.7 1B
- Granite 4.2 3B vs MiniCPM-V 4.7 35B-A3B
- Granite 4.2 3B vs MiniCPM5-2B
- Granite 4.2 3B vs MiniMax-M2.5
- Granite 4.2 3B vs MiniMax-M2.7
- Granite 4.2 3B vs MiniMax-M3.1-Flash
- Granite 4.2 3B vs Mistral Large 4
- Granite 4.2 3B vs Muse Glimmer 30B
- Granite 4.2 3B vs Nanbeige4.3-33B
- Granite 4.2 3B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Granite 4.2 3B vs Nemotron 3.5 Lightning 30B A3B
- Granite 4.2 3B vs Nemotron 3 Nano 30B A3B
- Granite 4.2 3B vs Nemotron 3 Nano 4B
- Granite 4.2 3B vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Granite 4.2 3B vs Nemotron 3 Super 120B A12B
- Granite 4.2 3B vs Nemotron 3 Ultra 550B A55B
- Granite 4.2 3B vs occamy-1.0
- Granite 4.2 3B vs Olmo 3 7B Think
- Granite 4.2 3B vs Ornith-1.5-122B
- Granite 4.2 3B vs Ornith-1.5-35B-A3B
- Granite 4.2 3B vs Ornith-1.5-397B
- Granite 4.2 3B vs Ornith-1.5-9B
- Granite 4.2 3B vs Qwen-AgentWorld-35B-A3B
- Granite 4.2 3B vs Qwen3-30B-A3B-Instruct-2507
- Granite 4.2 3B vs Qwen3-4B-Instruct-2507
- Granite 4.2 3B vs Qwen3.5-0.8B
- Granite 4.2 3B vs Qwen3.5-122B-A10B
- Granite 4.2 3B vs Qwen3.5-2B
- Granite 4.2 3B vs Qwen3.5-397B-A17B
- Granite 4.2 3B vs Qwen3.5-4B
- Granite 4.2 3B vs Qwen3.5-9B
- Granite 4.2 3B vs Qwen3.6-27B
- Granite 4.2 3B vs Qwen3.6-35B-A3B
- Granite 4.2 3B vs Qwen3.8-27B
- Granite 4.2 3B vs Qwen3.8-Flash-Next
- Granite 4.2 3B vs Qwen3-Coder-30B-A3B-Instruct
- Granite 4.2 3B vs Qwen3-Coder-Next
- Granite 4.2 3B vs Qwen3-Omni-30B-A3B-Instruct
- Granite 4.2 3B vs Qwen3-VL-2B-Instruct
- Granite 4.2 3B vs Qwen3-VL-30B-A3B-Instruct
- Granite 4.2 3B vs Qwen3-VL-32B-Instruct
- Granite 4.2 3B vs Qwen3-VL-4B-Instruct
- Granite 4.2 3B vs Qwen3-VL-8B-Instruct
- Granite 4.2 3B vs Qwopus3.8-27B-Flash-V2
- Granite 4.2 3B vs Recursive Flint
- Granite 4.2 3B vs Ripple-65B Preview
- Granite 4.2 3B vs SmolLM3-3B
- Granite 4.2 3B vs Spark-X2.6-4B
- Granite 4.2 3B vs Swift 1.5 Qwen3.8-27B
- Granite 4.2 3B vs Swift 1.5 Qwen3.8-Flash-Next
- Granite 4.2 3B vs ThinkingCap (Qwen3.8 27B)
- Granite 4.2 3B vs Baidu Unlimited-OCR-2
- Granite 4.2 8B vs Hy-Memory-30B-A3B
- Hy-Memory-30B-A3B vs Hy3
- Hy-Memory-30B-A3B vs Inkling
- Hy-Memory-30B-A3B vs Inkling-Small
- Hy-Memory-30B-A3B vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Hy-Memory-30B-A3B vs Kimi K3
- Hy-Memory-30B-A3B vs Kimi K3.1 Pro
- Hy-Memory-30B-A3B vs Kolibri-1
- Hy-Memory-30B-A3B vs Kronos
- Hy-Memory-30B-A3B vs Laguna M.1
- Hy-Memory-30B-A3B vs Laguna S 2.1
- Hy-Memory-30B-A3B vs Laguna XS 2.1
- Hy-Memory-30B-A3B vs LBS-27B
- Hy-Memory-30B-A3B vs LFM2.5-2.6B
- Hy-Memory-30B-A3B vs LFM3-1.7B
- Hy-Memory-30B-A3B vs LFM3-Audio-2B
- Hy-Memory-30B-A3B vs LFM3-Omni-2B
- Hy-Memory-30B-A3B vs LFM3-VL-2B
- Hy-Memory-30B-A3B vs Ling-3.0-tiny
- Hy-Memory-30B-A3B vs Ling-3.1-flash-1019
- Hy-Memory-30B-A3B vs MiMo-V2.6 Distill Qwen 9B
- Hy-Memory-30B-A3B vs MiniCPM-o 4.5
- Hy-Memory-30B-A3B vs MiniCPM-V 4.7 1B
- Hy-Memory-30B-A3B vs MiniCPM-V 4.7 35B-A3B
- Hy-Memory-30B-A3B vs MiniCPM5-2B
- Hy-Memory-30B-A3B vs MiniMax-M2.5
- Hy-Memory-30B-A3B vs MiniMax-M2.7
- Hy-Memory-30B-A3B vs MiniMax-M3.1-Flash
- Hy-Memory-30B-A3B vs Mistral Large 4
- Hy-Memory-30B-A3B vs Muse Glimmer 30B
- Hy-Memory-30B-A3B vs Nanbeige4.3-33B
- Hy-Memory-30B-A3B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Hy-Memory-30B-A3B vs Nemotron 3.5 Lightning 30B A3B
- Hy-Memory-30B-A3B vs Nemotron 3 Nano 30B A3B
- Hy-Memory-30B-A3B vs Nemotron 3 Nano 4B
- Hy-Memory-30B-A3B vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Hy-Memory-30B-A3B vs Nemotron 3 Super 120B A12B
- Hy-Memory-30B-A3B vs Nemotron 3 Ultra 550B A55B
- Hy-Memory-30B-A3B vs occamy-1.0
- Hy-Memory-30B-A3B vs Olmo 3 7B Think
- Hy-Memory-30B-A3B vs Ornith-1.5-122B
- Hy-Memory-30B-A3B vs Ornith-1.5-35B-A3B
- Hy-Memory-30B-A3B vs Ornith-1.5-397B
- Hy-Memory-30B-A3B vs Ornith-1.5-9B
- Hy-Memory-30B-A3B vs Qwen-AgentWorld-35B-A3B
- Hy-Memory-30B-A3B vs Qwen3-30B-A3B-Instruct-2507
- Hy-Memory-30B-A3B vs Qwen3-4B-Instruct-2507
- Hy-Memory-30B-A3B vs Qwen3.5-0.8B
- Hy-Memory-30B-A3B vs Qwen3.5-122B-A10B
- Hy-Memory-30B-A3B vs Qwen3.5-2B
- Hy-Memory-30B-A3B vs Qwen3.5-397B-A17B
- Hy-Memory-30B-A3B vs Qwen3.5-4B
- Hy-Memory-30B-A3B vs Qwen3.5-9B
- Hy-Memory-30B-A3B vs Qwen3.6-27B
- Hy-Memory-30B-A3B vs Qwen3.6-35B-A3B
- Hy-Memory-30B-A3B vs Qwen3.8-27B
- Hy-Memory-30B-A3B vs Qwen3.8-Flash-Next
- Hy-Memory-30B-A3B vs Qwen3-Coder-30B-A3B-Instruct
- Hy-Memory-30B-A3B vs Qwen3-Coder-Next
- Hy-Memory-30B-A3B vs Qwen3-Omni-30B-A3B-Instruct
- Hy-Memory-30B-A3B vs Qwen3-VL-2B-Instruct
- Hy-Memory-30B-A3B vs Qwen3-VL-30B-A3B-Instruct
- Hy-Memory-30B-A3B vs Qwen3-VL-32B-Instruct
- Hy-Memory-30B-A3B vs Qwen3-VL-4B-Instruct
- Hy-Memory-30B-A3B vs Qwen3-VL-8B-Instruct
- Hy-Memory-30B-A3B vs Qwopus3.8-27B-Flash-V2
- Hy-Memory-30B-A3B vs Recursive Flint
- Hy-Memory-30B-A3B vs Ripple-65B Preview
- Hy-Memory-30B-A3B vs SmolLM3-3B
- Hy-Memory-30B-A3B vs Spark-X2.6-4B
- Hy-Memory-30B-A3B vs Swift 1.5 Qwen3.8-27B
- Hy-Memory-30B-A3B vs Swift 1.5 Qwen3.8-Flash-Next
- Hy-Memory-30B-A3B vs ThinkingCap (Qwen3.8 27B)
- Hy-Memory-30B-A3B vs Baidu Unlimited-OCR-2
Machine-readable
- This page as Markdown
/compare/granite-4-2-3b-vs-hy-memory-30b-a3b.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/granite-4-2-3b.json·/api/v1/tools/hy-memory-30b-a3b.json - From a terminal
anchor compare granite-4-2-3b hy-memory-30b-a3b(the CLI) - Over MCP
compare_tools {"a": "granite-4-2-3b", "b": "hy-memory-30b-a3b"}at/mcp, no key