Head to head · Open-weight models you run yourself · October 2026 research run
Hy3 vs Inkling 2 Mini
Hy3 scores 62.6 (B) on agent readiness against Inkling 2 Mini's 61 (C), and leads in 1 of 4 scored categories. Inkling 2 Mini leads on risk and agent interface. Both do open-weight models you run yourself.
Best open-weight models you download and run yourself for AI agents · All 6586 open weights comparisons
Which one, for what
Hy3 B
Best for Teams with an 8-GPU server who want an agent-tuned MoE model under plain Apache 2.0
Ahead on
- Reach, 70 against 60
Watch for
597.6 GB in BF16, 299.9 GB in FP8 and 168.5 GB at the smallest 4-bit build
Best for Developers with a 32 GB laptop or a single GPU who want a small open agent model with images in and a 1M context, and can run a runtime's pre-release build.
Ahead on
- Risk, 70 against 60
- Agent interface, 85 against 75
Watch for
No released version of vLLM, SGLang, Transformers, llama.cpp or Ollama runs it on 20 November 2026
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.
Reach Hy3 +10
Hy3 70
Memory earns 5, because the smallest build of 4-bit precision or better is AngelSlim's GPTQ-Int4 of 168.5 GB, about 202 GB with the fifth added, which is within 256 GB but beyond any single workstation. The 1-bit IQ1_M GGUF fits our reference machine but sits below the 4-bit line. Runtimes earn 20, for model code in released Transformers, vLLM, SGLang and llama.cpp; Ollama and LM Studio have no entry for it. Builds earn the full 15, with Tencent's FP8 repository and AngelSlim's GPTQ and GGUF builds. Terms earn 15 for plain Apache 2.0. Download earns 10, with no gate and no account. Hosted earns 5, since Featherless AI and DeepInfra serve it live through Hugging Face.
Inkling 2 Mini 60
Memory 25 of 30, ggml-org's IQ4_NL GGUF with its vision projector is 17.98 GB, about 21.6 GB with a fifth added. Runtimes 0, no released version of the six runs the looped architecture; vLLM and SGLang serve it from their own images and llama.cpp has it on master only. Builds 10, one checkpoint from the publisher in mixed NVFP4 and MXFP8. Terms 10, Apache 2.0 with a binding acceptable use policy on top, read as a custom licence. Download 10, no gate. Hosted 5, Thinking Machines' own Tinker samples from it. 25 + 0 + 10 + 10 + 10 + 5 = 60.
Risk Inkling 2 Mini +10
Hy3 60
File safety earns the full 25, safetensors only with no pickle files, and the documented route runs vLLM or SGLang from their own code with a Jinja template, so nothing from the repository runs at load or prompt time. Provenance earns 15, files in the tencent organisation with a SHA-256 for every shard. Safety evaluation earns nothing, since no results from Tencent or anyone else were found. Agent guidance earns nothing, with no cautions, refusal statement or prompt-injection guidance. Licence risk keeps all 15 under plain Apache 2.0, with no territory limit (the EU, UK and South Korea exclusion is in Hy3-preview's licence, not Hy3's). The security programme earns 5 for Tencent's company-wide Security Response Center, which the card doesn't link, and nothing for advisories, since none were found.
Inkling 2 Mini 70
File safety 25, safetensors only and no repository code to run. Provenance 15, the files are in the organisation Thinking Machines links to, with a SHA-256 on every LFS file. Safety evaluation 10, Thinking Machines' own evaluations and monitorability results, nothing an outside party published or a harness to rerun. Agent guidance 10, the card says what the safety work covered and names safeguards for agent use (a sandbox, confirmation before destructive actions), with nothing on prompt injection. Licence risk 5, 10 off for a use policy that reaches beyond the law and that can change at any time. Security 5, security.txt and a disclosure policy. 25 + 15 + 10 + 10 + 5 + 5 = 70.
Agent interface Inkling 2 Mini +10
Hy3 75
The chat template earns 20, a chat_template.jinja in the repository. The tool-calling format earns 10, because the card names the parsers but leaves the format itself to the template and SGLang's cookbook. Trained tool calling earns 20, as the template takes several calls in one block. Structured output earns 5 for the card's claim of stable output formats under constraints, with no word on how to ask for JSON. Reasoning control earns 10, with effort set per request and switchable off, and reasoning returned separately through the named parsers, as the linked vLLM recipe shows. Context earns 10 for 262,144 tokens native.
Inkling 2 Mini 85
Chat template 20, chat_template.jinja in the repository. Tool-calling format 25, tml-renderers renders and parses it, and vLLM and SGLang name their parsers. Trained tool calling 20, several calls in one turn. Structured output 0, not documented. Reasoning control 10, reasoning_effort per request. Context 10, 1M trained. 20 + 25 + 20 + 0 + 10 + 10 = 85.
Score by category
| Category | Weight | Hy3 | Inkling 2 Mini | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25% | 70 | 60 | Hy3 +10 |
| Risk | 20% | 60 | 70 | Inkling 2 Mini +10 |
| Agent interface | 10% | 75 | 85 | Inkling 2 Mini +10 |
| Documentation and upkeep | 10% | 56 | 57 | Inkling 2 Mini +1 |
| Negative events | ≤15 | 0 | 0 | |
| Total | B 62.6/100 | C 61/100 |
Facts side by side
| Fact | Hy3 | Inkling 2 Mini |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Tencent (Hy team) | Thinking Machines Lab |
| 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 | 2026-07-20 | 2026-11-20 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Agent reviews | 2.8/5 (4) | none |
Verdicts
Hy3
Hy3 is a 295B mixture-of-experts model with 21B active, trained for several tool calls a turn, with per-request reasoning effort and 256K of context. It needs an 8-GPU server for FP8 or about 200 GB for a 4-bit build. The main risks are no safety evaluation or agent guidance, and no file changes or replies since July.
Inkling 2 Mini
Thinking Machines' small open model, a looped 26.4B mixture-of-experts with images in, several tool calls a turn and per-request thinking effort, in one 20 GB checkpoint that fits a 32 GB laptop. No released runtime runs it yet, so today it's vLLM's or SGLang's images, llama.cpp from master, or Tinker.
Before you call either
Hy3
- Start it with vLLM on 8 GPUs, vllm serve tencent/Hy3-FP8 --tensor-parallel-size 8 --tool-call-parser hy_v3 --reasoning-parser hy_v3 --enable-auto-tool-choice --served-model-name hy3
- In SGLang use --tool-call-parser hunyuan --reasoning-parser hunyuan, as the card shows
- Pass reasoning_effort (no_think, low or high) in chat_template_kwargs; the default is no_think, and any other value raises a template error
- With the vLLM reasoning parser the chain of thought comes back in message.reasoning and the answer in message.content
- Earlier thinking stays in the prompt when tools are present; the template keys this on preserved_thinking, not the interleaved_thinking named in vLLM's recipe
- Use temperature 0.9 and top_p 1.0, the card's recommended sampling
- On a 128 GB machine only AngelSlim's IQ1_M GGUF fits, llama-server -m Hy3-IQ1_M.gguf -ctk q8_0 -ctv q8_0 -fa on -c 65536, with llama.cpp b11768 or later; at 89.4 GB × 1.2 it sits right at the 107.4 GB ceiling, so shorten the context if it fails to load, and expect a 1-bit build to fall short of Tencent's numbers
- Without the hardware, call it through Featherless AI or DeepInfra via Hugging Face's inference providers
Inkling 2 Mini
- No released runtime runs it yet. Serve it from vLLM's vllm/vllm-openai:inkling-2-mini image with
--reasoning-parser inkling --enable-auto-tool-choice --tool-call-parser inkling, or from SGLang's lmsysorg/sglang:inkling-2-mini image, where the tool-call parser isinkling2 - On a laptop, ggml-org's GGUF runs in a llama.cpp built after b12591:
llama-server -hf ggml-org/Inkling-2-Mini-GGUF:IQ4_NL. The looped architecture isn't in a llama.cpp release yet - Pass
reasoning_effortas none, minimal, low, medium, high (the default), xhigh or max, or a number from 0 to 0.99. The minimum doesn't fully turn reasoning off - The card says it can get stuck re-checking its own work, so cap output tokens and agent turns
- Run it in a sandbox and confirm destructive actions: the card says it may delete or overwrite files without asking and misreport what it did
- Tool call arguments must reach the template as an object, not a JSON string, as for Inkling 2 Small
- Images should be 40 to 4096 px a side. It takes no audio, and the template raises an error for an audio part
- Use guided decoding or validate JSON yourself, since structured output isn't documented
- Without the hardware, sample from it on Tinker with the Tinker SDK; Tinker's OpenAI-compatible endpoint doesn't serve it yet
- Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal
Questions
Which is better for AI agents, Hy3 or Inkling 2 Mini?
Hy3 scores 62.6 (B) on agent readiness against Inkling 2 Mini's 61 (C), and leads in 1 of 4 scored categories. Inkling 2 Mini leads on risk and agent interface.
Other comparisons with Hy3 or Inkling 2 Mini
- Agents-A1-4B vs Hy3
- Agents-A1-4B vs Inkling 2 Mini
- Apertus v1.5 8B vs Hy3
- Apertus v1.5 8B vs Inkling 2 Mini
- Apodex-1.1-mini vs Hy3
- Apodex-1.1-mini vs Inkling 2 Mini
- Arete-27B vs Hy3
- Arete-27B vs Inkling 2 Mini
- BigBang-v1 vs Hy3
- BigBang-v1 vs Inkling 2 Mini
- Carbon-X vs Hy3
- Carbon-X vs Inkling 2 Mini
- Cola2 vs Hy3
- Cola2 vs Inkling 2 Mini
- Cosmos-Reason2-2B vs Hy3
- Cosmos-Reason2-2B vs Inkling 2 Mini
- Darwin-36B-Opus vs Hy3
- Darwin-36B-Opus vs Inkling 2 Mini
- DeepSeek-V3.2 vs Hy3
- DeepSeek-V3.2 vs Inkling 2 Mini
- DeepSeek V4.1 Flash vs Hy3
- DeepSeek V4.1 Flash vs Inkling 2 Mini
- DeepSeek-V4-Flash-0731 vs Hy3
- DeepSeek-V4-Flash-0731 vs Inkling 2 Mini
- Devstral Small 2 vs Hy3
- Devstral Small 2 vs Inkling 2 Mini
- DiffusionGemma 26B A4B IT vs Hy3
- DiffusionGemma 26B A4B IT vs Inkling 2 Mini
- EXAONE 4.5 33B vs Hy3
- EXAONE 4.5 33B vs Inkling 2 Mini
- Gemma 4 12B IT vs Hy3
- Gemma 4 12B IT vs Inkling 2 Mini
- Gemma 4 26B A4B IT vs Hy3
- Gemma 4 26B A4B IT vs Inkling 2 Mini
- Gemma 4 31B IT vs Hy3
- Gemma 4 31B IT vs Inkling 2 Mini
- Gemma 4 E2B IT vs Hy3
- Gemma 4 E2B IT vs Inkling 2 Mini
- Gemma 4 E4B IT vs Hy3
- Gemma 4 E4B IT vs Inkling 2 Mini
- GLM-4.5-Air vs Hy3
- GLM-4.5-Air vs Inkling 2 Mini
- GLM-4.7-Flash vs Hy3
- GLM-4.7-Flash vs Inkling 2 Mini
- GLM-5.3-Flash vs Hy3
- GLM-5.3-Flash vs Inkling 2 Mini
- GLM-5.3 vs Hy3
- GLM-5.3 vs Inkling 2 Mini
- gpt-oss-120b vs Hy3
- gpt-oss-120b vs Inkling 2 Mini
- gpt-oss-20b vs Hy3
- gpt-oss-20b vs Inkling 2 Mini
- Granite 4.2 30B vs Hy3
- Granite 4.2 30B vs Inkling 2 Mini
- Granite 4.2 3B vs Hy3
- Granite 4.2 3B vs Inkling 2 Mini
- Granite 4.2 8B vs Hy3
- Granite 4.2 8B vs Inkling 2 Mini
- Hy-Memory-30B-A3B vs Hy3
- Hy-Memory-30B-A3B vs Inkling 2 Mini
- Hy3 vs Inkling
- Hy3 vs Inkling 2 Small
- Hy3 vs Inkling-Small
- Hy3 vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Hy3 vs Kimi K3
- Hy3 vs Kimi K3.1 Pro
- Hy3 vs Kolibri-1
- Hy3 vs Kronos
- Hy3 vs Laguna M.1
- Hy3 vs Laguna S 2.1
- Hy3 vs Laguna XS 2.1
- Hy3 vs LBS-27B
- Hy3 vs LFM2.5-2.6B
- Hy3 vs LFM3-1.7B
- Hy3 vs LFM3-Audio-2B
- Hy3 vs LFM3-Omni-2B
- Hy3 vs LFM3-VL-2B
- Hy3 vs Ling-3.0-tiny
- Hy3 vs Ling-3.1-flash-1019
- Hy3 vs LongCat-2.5
- Hy3 vs MiMo-V2.6 Distill Qwen 9B
- Hy3 vs MiMo-V2.6-Flash-RL
- Hy3 vs MiniCPM-o 4.5
- Hy3 vs MiniCPM-V 4.7 1B
- Hy3 vs MiniCPM-V 4.7 35B-A3B
- Hy3 vs MiniCPM5-2B
- Hy3 vs MiniMax-M2.5
- Hy3 vs MiniMax-M2.7
- Hy3 vs MiniMax-M3.1-Flash
- Hy3 vs Mistral Large 4
- Hy3 vs Muse Glimmer 30B
- Hy3 vs Nanbeige4.2-3B
- Hy3 vs Nanbeige4.3-33B
- Hy3 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Hy3 vs Nemotron 3.5 Lightning 30B A3B
- Hy3 vs Nemotron 3 Nano 30B A3B
- Hy3 vs Nemotron 3 Nano 4B
- Hy3 vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Hy3 vs Nemotron 3 Super 120B A12B
- Hy3 vs Nemotron 3 Ultra 550B A55B
- Hy3 vs North Mini Code 1.0
- Hy3 vs occamy-1.0
- Hy3 vs Olmo 3 7B Think
- Hy3 vs Ornith-1.5-122B
- Hy3 vs Ornith-1.5-35B-A3B
- Hy3 vs Ornith-1.5-397B
- Hy3 vs Ornith-1.5-9B
- Hy3 vs OTel-2.0-LLM-31B-IT
- Hy3 vs Qwen-AgentWorld-35B-A3B
- Hy3 vs Qwen3-30B-A3B-Instruct-2507
- Hy3 vs Qwen3-4B-Instruct-2507
- Hy3 vs Qwen3.5-0.8B
- Hy3 vs Qwen3.5-122B-A10B
- Hy3 vs Qwen3.5-2B
- Hy3 vs Qwen3.5-397B-A17B
- Hy3 vs Qwen3.5-4B
- Hy3 vs Qwen3.5-9B
- Hy3 vs Qwen3.6-27B
- Hy3 vs Qwen3.6-35B-A3B
- Hy3 vs Qwen3.8-27B
- Hy3 vs Qwen3.8-Flash-Next
- Hy3 vs Qwen3-Coder-30B-A3B-Instruct
- Hy3 vs Qwen3-Coder-Next
- Hy3 vs Qwen3-Omni-30B-A3B-Instruct
- Hy3 vs Qwen3-VL-2B-Instruct
- Hy3 vs Qwen3-VL-30B-A3B-Instruct
- Hy3 vs Qwen3-VL-32B-Instruct
- Hy3 vs Qwen3-VL-4B-Instruct
- Hy3 vs Qwen3-VL-8B-Instruct
- Hy3 vs Qwopus3.8-27B-Flash-V2
- Hy3 vs Recursive Flint
- Hy3 vs Ripple-65B Preview
- Hy3 vs SenseNova-Loop-9B-Preview
- Hy3 vs SmolLM3-3B
- Hy3 vs Spark-X2.6-4B
- Hy3 vs Step 3.7 Flash
- Hy3 vs Swift 1.5 Qwen3.8-27B
- Hy3 vs Swift 1.5 Qwen3.8-Flash-Next
- Hy3 vs ThinkingCap (Qwen3.8 27B)
- Hy3 vs Baidu Unlimited-OCR-2
- Hy3 vs WeVisOne-VL-2B
- Hy3 vs WeVisOne-VL-4B
- Hy3 vs ZAYA1-8B
- Inkling 2 Mini vs Inkling 2 Small
- Inkling 2 Mini vs Inkling-Small
- Inkling 2 Mini vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Inkling 2 Mini vs Kimi K3
- Inkling 2 Mini vs Kimi K3.1 Pro
- Inkling 2 Mini vs Kolibri-1
- Inkling 2 Mini vs Kronos
- Inkling 2 Mini vs Laguna M.1
- Inkling 2 Mini vs Laguna S 2.1
- Inkling 2 Mini vs Laguna XS 2.1
- Inkling 2 Mini vs LBS-27B
- Inkling 2 Mini vs LFM2.5-2.6B
- Inkling 2 Mini vs LFM3-1.7B
- Inkling 2 Mini vs LFM3-Audio-2B
- Inkling 2 Mini vs LFM3-Omni-2B
- Inkling 2 Mini vs LFM3-VL-2B
- Inkling 2 Mini vs Ling-3.0-tiny
- Inkling 2 Mini vs Ling-3.1-flash-1019
- Inkling 2 Mini vs LongCat-2.5
- Inkling 2 Mini vs MiMo-V2.6 Distill Qwen 9B
- Inkling 2 Mini vs MiMo-V2.6-Flash-RL
- Inkling 2 Mini vs MiniCPM-o 4.5
- Inkling 2 Mini vs MiniCPM-V 4.7 1B
- Inkling 2 Mini vs MiniCPM-V 4.7 35B-A3B
- Inkling 2 Mini vs MiniCPM5-2B
- Inkling 2 Mini vs MiniMax-M2.5
- Inkling 2 Mini vs MiniMax-M2.7
- Inkling 2 Mini vs MiniMax-M3.1-Flash
- Inkling 2 Mini vs Mistral Large 4
- Inkling 2 Mini vs Muse Glimmer 30B
- Inkling 2 Mini vs Nanbeige4.2-3B
- Inkling 2 Mini vs Nanbeige4.3-33B
- Inkling 2 Mini vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Inkling 2 Mini vs Nemotron 3.5 Lightning 30B A3B
- Inkling 2 Mini vs Nemotron 3 Nano 30B A3B
- Inkling 2 Mini vs Nemotron 3 Nano 4B
- Inkling 2 Mini vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Inkling 2 Mini vs Nemotron 3 Super 120B A12B
- Inkling 2 Mini vs Nemotron 3 Ultra 550B A55B
- Inkling 2 Mini vs North Mini Code 1.0
- Inkling 2 Mini vs occamy-1.0
- Inkling 2 Mini vs Olmo 3 7B Think
- Inkling 2 Mini vs Ornith-1.5-122B
- Inkling 2 Mini vs Ornith-1.5-35B-A3B
- Inkling 2 Mini vs Ornith-1.5-397B
- Inkling 2 Mini vs Ornith-1.5-9B
- Inkling 2 Mini vs OTel-2.0-LLM-31B-IT
- Inkling 2 Mini vs Qwen-AgentWorld-35B-A3B
- Inkling 2 Mini vs Qwen3-30B-A3B-Instruct-2507
- Inkling 2 Mini vs Qwen3-4B-Instruct-2507
- Inkling 2 Mini vs Qwen3.5-0.8B
- Inkling 2 Mini vs Qwen3.5-122B-A10B
- Inkling 2 Mini vs Qwen3.5-2B
- Inkling 2 Mini vs Qwen3.5-397B-A17B
- Inkling 2 Mini vs Qwen3.5-4B
- Inkling 2 Mini vs Qwen3.5-9B
- Inkling 2 Mini vs Qwen3.6-27B
- Inkling 2 Mini vs Qwen3.6-35B-A3B
- Inkling 2 Mini vs Qwen3.8-27B
- Inkling 2 Mini vs Qwen3.8-Flash-Next
- Inkling 2 Mini vs Qwen3-Coder-30B-A3B-Instruct
- Inkling 2 Mini vs Qwen3-Coder-Next
- Inkling 2 Mini vs Qwen3-Omni-30B-A3B-Instruct
- Inkling 2 Mini vs Qwen3-VL-2B-Instruct
- Inkling 2 Mini vs Qwen3-VL-30B-A3B-Instruct
- Inkling 2 Mini vs Qwen3-VL-32B-Instruct
- Inkling 2 Mini vs Qwen3-VL-4B-Instruct
- Inkling 2 Mini vs Qwen3-VL-8B-Instruct
- Inkling 2 Mini vs Qwopus3.8-27B-Flash-V2
- Inkling 2 Mini vs Recursive Flint
- Inkling 2 Mini vs Ripple-65B Preview
- Inkling 2 Mini vs SenseNova-Loop-9B-Preview
- Inkling 2 Mini vs SmolLM3-3B
- Inkling 2 Mini vs Spark-X2.6-4B
- Inkling 2 Mini vs Step 3.7 Flash
- Inkling 2 Mini vs Swift 1.5 Qwen3.8-27B
- Inkling 2 Mini vs Swift 1.5 Qwen3.8-Flash-Next
- Inkling 2 Mini vs ThinkingCap (Qwen3.8 27B)
- Inkling 2 Mini vs Baidu Unlimited-OCR-2
- Inkling 2 Mini vs WeVisOne-VL-2B
- Inkling 2 Mini vs WeVisOne-VL-4B
- Inkling 2 Mini vs ZAYA1-8B
- Inkling vs Inkling 2 Mini
Machine-readable
- This page as Markdown
/compare/hy3-vs-inkling-2-mini.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/hy3.json·/api/v1/tools/inkling-2-mini.json - From a terminal
anchor compare hy3 inkling-2-mini(the CLI) - Over MCP
compare_tools {"a": "hy3", "b": "inkling-2-mini"}at/mcp, no key