Head to head · Open-weight models you run yourself · October 2026 research run
Inkling 2 Mini vs Nanbeige4.3-33B
Inkling 2 Mini 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 reach. 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
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
Watch for
No released version of vLLM, SGLang, Transformers, llama.cpp or Ollama runs it on 20 November 2026
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
- Reach, 80 against 60
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.
Reach Nanbeige4.3-33B +20
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.
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.
Risk Inkling 2 Mini +10
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.
Nanbeige4.3-33B 60
File safety earns 25, safetensors only and no repository code, so the card's trust_remote_code has nothing to run. Provenance earns 15, the lab's own organisation as its arXiv report links it, with a hash for every file. Safety evaluation earns 0 and agent guidance 0, since neither card says anything on either. Licence risk keeps all 15 under Apache 2.0. The security programme earns 5 for BOSS Zhipin's security response centre, which isn't linked to the model.
Score by category
| Category | Weight | Inkling 2 Mini | Nanbeige4.3-33B | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25% | 60 | 80 | Nanbeige4.3-33B +20 |
| Risk | 20% | 70 | 60 | Inkling 2 Mini +10 |
| Agent interface | 10% | 85 | 85 | even |
| Documentation and upkeep | 10% | 57 | 56 | Inkling 2 Mini +1 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | C 60.8/100 |
Facts side by side
| Fact | Inkling 2 Mini | Nanbeige4.3-33B |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Thinking Machines Lab | Nanbeige LLM Lab (BOSS Zhipin) |
| 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 (Hub metadata only; the repository has no LICENSE file) |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-11-20 | 2026-10-31 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
How the scores have moved
Inkling 2 Mini
No score change since it was listed.
Verdicts
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.
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
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
Nanbeige4.3-33B
- 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 - 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
- Keep
tool_call_formatat its defaultxml, since qwen3_coder parses that format; thejsonoption writes Hermes-style JSON calls, which need a different parser such as vLLM's hermes - 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 - 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
- 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
- Send one system message at the start only, as the template raises an error for a later one
- In plain Transformers pass
use_cache=Trueto generate, since config.json and generation_config.json set it false; trust_remote_code isn't needed
Questions
Which is better for AI agents, Inkling 2 Mini or Nanbeige4.3-33B?
Inkling 2 Mini 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 reach.
Other comparisons with Inkling 2 Mini or Nanbeige4.3-33B
- Agents-A1-4B vs Inkling 2 Mini
- Agents-A1-4B vs Nanbeige4.3-33B
- Apertus v1.5 8B vs Inkling 2 Mini
- Apertus v1.5 8B vs Nanbeige4.3-33B
- Apodex-1.1-mini vs Inkling 2 Mini
- Apodex-1.1-mini vs Nanbeige4.3-33B
- Arete-27B vs Inkling 2 Mini
- Arete-27B vs Nanbeige4.3-33B
- BigBang-v1 vs Inkling 2 Mini
- BigBang-v1 vs Nanbeige4.3-33B
- Carbon-X vs Inkling 2 Mini
- Carbon-X vs Nanbeige4.3-33B
- Cola2 vs Inkling 2 Mini
- Cola2 vs Nanbeige4.3-33B
- Cosmos-Reason2-2B vs Inkling 2 Mini
- Cosmos-Reason2-2B vs Nanbeige4.3-33B
- Darwin-36B-Opus vs Inkling 2 Mini
- Darwin-36B-Opus vs Nanbeige4.3-33B
- DeepSeek-V3.2 vs Inkling 2 Mini
- DeepSeek-V3.2 vs Nanbeige4.3-33B
- DeepSeek V4.1 Flash vs Inkling 2 Mini
- DeepSeek V4.1 Flash vs Nanbeige4.3-33B
- DeepSeek-V4-Flash-0731 vs Inkling 2 Mini
- DeepSeek-V4-Flash-0731 vs Nanbeige4.3-33B
- Devstral Small 2 vs Inkling 2 Mini
- Devstral Small 2 vs Nanbeige4.3-33B
- DiffusionGemma 26B A4B IT vs Inkling 2 Mini
- DiffusionGemma 26B A4B IT vs Nanbeige4.3-33B
- EXAONE 4.5 33B vs Inkling 2 Mini
- EXAONE 4.5 33B vs Nanbeige4.3-33B
- Gemma 4 12B IT vs Inkling 2 Mini
- Gemma 4 12B IT vs Nanbeige4.3-33B
- Gemma 4 26B A4B IT vs Inkling 2 Mini
- Gemma 4 26B A4B IT vs Nanbeige4.3-33B
- Gemma 4 31B IT vs Inkling 2 Mini
- Gemma 4 31B IT vs Nanbeige4.3-33B
- Gemma 4 E2B IT vs Inkling 2 Mini
- Gemma 4 E2B IT vs Nanbeige4.3-33B
- Gemma 4 E4B IT vs Inkling 2 Mini
- Gemma 4 E4B IT vs Nanbeige4.3-33B
- GLM-4.5-Air vs Inkling 2 Mini
- GLM-4.5-Air vs Nanbeige4.3-33B
- GLM-4.7-Flash vs Inkling 2 Mini
- GLM-4.7-Flash vs Nanbeige4.3-33B
- GLM-5.3-Flash vs Inkling 2 Mini
- GLM-5.3-Flash vs Nanbeige4.3-33B
- GLM-5.3 vs Inkling 2 Mini
- GLM-5.3 vs Nanbeige4.3-33B
- gpt-oss-120b vs Inkling 2 Mini
- gpt-oss-120b vs Nanbeige4.3-33B
- gpt-oss-20b vs Inkling 2 Mini
- gpt-oss-20b vs Nanbeige4.3-33B
- Granite 4.2 30B vs Inkling 2 Mini
- Granite 4.2 30B vs Nanbeige4.3-33B
- Granite 4.2 3B vs Inkling 2 Mini
- Granite 4.2 3B vs Nanbeige4.3-33B
- Granite 4.2 8B vs Inkling 2 Mini
- Granite 4.2 8B vs Nanbeige4.3-33B
- Hy-Memory-30B-A3B vs Inkling 2 Mini
- Hy-Memory-30B-A3B vs Nanbeige4.3-33B
- Hy3 vs Inkling 2 Mini
- Hy3 vs Nanbeige4.3-33B
- 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 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 2 Small vs Nanbeige4.3-33B
- Inkling-Small vs Nanbeige4.3-33B
- Inkling vs Inkling 2 Mini
- Inkling vs Nanbeige4.3-33B
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs Nanbeige4.3-33B
- Kimi K3.1 Pro vs Nanbeige4.3-33B
- Kimi K3 vs Nanbeige4.3-33B
- Kolibri-1 vs Nanbeige4.3-33B
- Kronos vs Nanbeige4.3-33B
- Laguna M.1 vs Nanbeige4.3-33B
- Laguna S 2.1 vs Nanbeige4.3-33B
- Laguna XS 2.1 vs Nanbeige4.3-33B
- LBS-27B vs Nanbeige4.3-33B
- LFM2.5-2.6B vs Nanbeige4.3-33B
- LFM3-1.7B vs Nanbeige4.3-33B
- LFM3-Audio-2B vs Nanbeige4.3-33B
- LFM3-Omni-2B vs Nanbeige4.3-33B
- LFM3-VL-2B vs Nanbeige4.3-33B
- Ling-3.0-tiny vs Nanbeige4.3-33B
- Ling-3.1-flash-1019 vs Nanbeige4.3-33B
- LongCat-2.5 vs Nanbeige4.3-33B
- MiMo-V2.6 Distill Qwen 9B vs Nanbeige4.3-33B
- MiMo-V2.6-Flash-RL vs Nanbeige4.3-33B
- MiniCPM-o 4.5 vs Nanbeige4.3-33B
- MiniCPM-V 4.7 1B vs Nanbeige4.3-33B
- MiniCPM-V 4.7 35B-A3B vs Nanbeige4.3-33B
- MiniCPM5-2B vs Nanbeige4.3-33B
- MiniMax-M2.5 vs Nanbeige4.3-33B
- MiniMax-M2.7 vs Nanbeige4.3-33B
- MiniMax-M3.1-Flash vs Nanbeige4.3-33B
- Mistral Large 4 vs Nanbeige4.3-33B
- Muse Glimmer 30B vs Nanbeige4.3-33B
- Nanbeige4.2-3B vs Nanbeige4.3-33B
- Nanbeige4.3-33B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Nanbeige4.3-33B vs Nemotron 3.5 Lightning 30B A3B
- Nanbeige4.3-33B vs Nemotron 3 Nano 30B A3B
- Nanbeige4.3-33B vs Nemotron 3 Nano 4B
- Nanbeige4.3-33B vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Nanbeige4.3-33B vs Nemotron 3 Super 120B A12B
- Nanbeige4.3-33B vs Nemotron 3 Ultra 550B A55B
- Nanbeige4.3-33B vs North Mini Code 1.0
- Nanbeige4.3-33B vs occamy-1.0
- Nanbeige4.3-33B vs Olmo 3 7B Think
- Nanbeige4.3-33B vs Ornith-1.5-122B
- Nanbeige4.3-33B vs Ornith-1.5-35B-A3B
- Nanbeige4.3-33B vs Ornith-1.5-397B
- Nanbeige4.3-33B vs Ornith-1.5-9B
- Nanbeige4.3-33B vs OTel-2.0-LLM-31B-IT
- Nanbeige4.3-33B vs Qwen-AgentWorld-35B-A3B
- Nanbeige4.3-33B vs Qwen3-30B-A3B-Instruct-2507
- Nanbeige4.3-33B vs Qwen3-4B-Instruct-2507
- Nanbeige4.3-33B vs Qwen3.5-0.8B
- Nanbeige4.3-33B vs Qwen3.5-122B-A10B
- Nanbeige4.3-33B vs Qwen3.5-2B
- Nanbeige4.3-33B vs Qwen3.5-397B-A17B
- Nanbeige4.3-33B vs Qwen3.5-4B
- Nanbeige4.3-33B vs Qwen3.5-9B
- Nanbeige4.3-33B vs Qwen3.6-27B
- Nanbeige4.3-33B vs Qwen3.6-35B-A3B
- Nanbeige4.3-33B vs Qwen3.8-27B
- Nanbeige4.3-33B vs Qwen3.8-Flash-Next
- Nanbeige4.3-33B vs Qwen3-Coder-30B-A3B-Instruct
- Nanbeige4.3-33B vs Qwen3-Coder-Next
- Nanbeige4.3-33B vs Qwen3-Omni-30B-A3B-Instruct
- Nanbeige4.3-33B vs Qwen3-VL-2B-Instruct
- Nanbeige4.3-33B vs Qwen3-VL-30B-A3B-Instruct
- Nanbeige4.3-33B vs Qwen3-VL-32B-Instruct
- Nanbeige4.3-33B vs Qwen3-VL-4B-Instruct
- Nanbeige4.3-33B vs Qwen3-VL-8B-Instruct
- Nanbeige4.3-33B vs Qwopus3.8-27B-Flash-V2
- Nanbeige4.3-33B vs Recursive Flint
- Nanbeige4.3-33B vs Ripple-65B Preview
- Nanbeige4.3-33B vs SenseNova-Loop-9B-Preview
- Nanbeige4.3-33B vs SmolLM3-3B
- Nanbeige4.3-33B vs Spark-X2.6-4B
- Nanbeige4.3-33B vs Step 3.7 Flash
- Nanbeige4.3-33B vs Swift 1.5 Qwen3.8-27B
- Nanbeige4.3-33B vs Swift 1.5 Qwen3.8-Flash-Next
- Nanbeige4.3-33B vs ThinkingCap (Qwen3.8 27B)
- Nanbeige4.3-33B vs Baidu Unlimited-OCR-2
- Nanbeige4.3-33B vs WeVisOne-VL-2B
- Nanbeige4.3-33B vs WeVisOne-VL-4B
- Nanbeige4.3-33B vs ZAYA1-8B
Machine-readable
- This page as Markdown
/compare/inkling-2-mini-vs-nanbeige-4-3-33b.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/inkling-2-mini.json·/api/v1/tools/nanbeige-4-3-33b.json - From a terminal
anchor compare inkling-2-mini nanbeige-4-3-33b(the CLI) - Over MCP
compare_tools {"a": "inkling-2-mini", "b": "nanbeige-4-3-33b"}at/mcp, no key