Head to head · Open-weight models you run yourself · October 2026 research run
Cola2 vs Inkling 2 Mini
Inkling 2 Mini scores 61 (C) on agent readiness against Cola2's 33.9 (F), 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 6586 open weights comparisons
Which one, for what
Cola2 F
Best for Researchers working on latent or diffusion language models who want a checkpoint to study
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
No licence stated for the weights
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
- Reach, 60 against 25
- Risk, 70 against 40
- Agent interface, 85 against 20
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.
Agent interface Inkling 2 Mini +65
Cola2 20
Chat template 20, A chat template in tokenizer_config.json (4,116 characters), which came with the Qwen3 tokeniser. Tool-calling format 0, none. Trained tool calling 0, not trained for tool calling. Structured output 0, Nothing about JSON or schema-constrained output. Reasoning control 0, no reasoning mode. Context 0, no context length is stated. 20 + 0 + 0 + 0 + 0 + 0 = 20.
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.
Reach Inkling 2 Mini +35
Cola2 25
Memory 15, the only build is the F32 safetensors set, 35.07 GB, and 35.07 GB × 1.2 = 42.1 GB, within 64 GB. Loaded as BF16, as the card's example does, it needs about half, but the line reads the file size. Runtimes 0, none of the six runs it in a released version. Builds 0, one set of weights and no quantised build. Terms 0, no licence for the weights. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it, and nothing names an API that serves it. 15 + 0 + 0 + 0 + 10 + 0 = 25.
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 +30
Cola2 40
File safety 15, safetensors only, no .bin, .pt or .pth files (25). Provenance 15, the files sit in the ByteDance-Seed organisation, which the ByteDance-Seed GitHub repository for the model links to (10). Safety evaluation 0, no safety results. Agent guidance 5, General cautions in the GitHub model card: not instruction-tuned or safety-aligned, not for use as an assistant, for facts or advice, or for high-impact decisions about people. Licence risk 0, With no licence for the weights there is nothing to hold ByteDance to. Security programme 5, the GitHub repository's SECURITY.md sends reports to ByteDance's security centre and says how they're assessed (5). 15 + 15 + 0 + 5 + 0 + 5 = 40.
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.
Score by category
| Category | Weight | Cola2 | Inkling 2 Mini | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25% | 25 | 60 | Inkling 2 Mini +35 |
| Risk | 20% | 40 | 70 | Inkling 2 Mini +30 |
| Agent interface | 10% | 20 | 85 | Inkling 2 Mini +65 |
| Documentation and upkeep | 10% | 58 | 57 | Cola2 +1 |
| Negative events | ≤15 | 0 | 0 | |
| Total | F 33.9/100 | C 61/100 |
Facts side by side
| Fact | Cola2 | Inkling 2 Mini |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | ByteDance (Seed) | Thinking Machines Lab |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | None stated for the weights (the code is Apache 2.0) | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-11-06 | 2026-11-20 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
Verdicts
Cola2
A research release, and an honest one: ByteDance Seed says it's a base model with an unconverged latent stage, scoring below Llama-3-8B on its own table. It's here for people studying continuous-latent generation. Agents can't use it as a model: 32-token completions, no chat or tools, the repository's own code to load it, and no licence on the weights.
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
Cola2
- Don't plan to use this as your model. It completes short prompts and wasn't tuned to follow instructions
- Don't use it commercially on the strength of this listing. The weights have no stated licence
- If you study it, read modeling_cola2.py first: trust_remote_code runs it
- Pin Transformers below 5, as the card requires
- Pass a seeded torch.Generator to generate(). Output varies between runs even with greedy decoding
- Check the download with
sha256sum -c SHA256SUMS
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, Cola2 or Inkling 2 Mini?
Inkling 2 Mini scores 61 (C) on agent readiness against Cola2's 33.9 (F), and leads in 3 of 4 scored categories.
Other comparisons with Cola2 or Inkling 2 Mini
- Agents-A1-4B vs Cola2
- Agents-A1-4B vs Inkling 2 Mini
- Apertus v1.5 8B vs Cola2
- Apertus v1.5 8B vs Inkling 2 Mini
- Apodex-1.1-mini vs Cola2
- Apodex-1.1-mini vs Inkling 2 Mini
- Arete-27B vs Cola2
- Arete-27B vs Inkling 2 Mini
- BigBang-v1 vs Cola2
- BigBang-v1 vs Inkling 2 Mini
- Carbon-X vs Cola2
- Carbon-X vs Inkling 2 Mini
- Cola2 vs Cosmos-Reason2-2B
- Cola2 vs Darwin-36B-Opus
- Cola2 vs DeepSeek-V3.2
- Cola2 vs DeepSeek V4.1 Flash
- Cola2 vs DeepSeek-V4-Flash-0731
- Cola2 vs Devstral Small 2
- Cola2 vs DiffusionGemma 26B A4B IT
- Cola2 vs EXAONE 4.5 33B
- Cola2 vs Gemma 4 12B IT
- Cola2 vs Gemma 4 26B A4B IT
- Cola2 vs Gemma 4 31B IT
- Cola2 vs Gemma 4 E2B IT
- Cola2 vs Gemma 4 E4B IT
- Cola2 vs GLM-4.5-Air
- Cola2 vs GLM-4.7-Flash
- Cola2 vs GLM-5.3
- Cola2 vs GLM-5.3-Flash
- Cola2 vs gpt-oss-120b
- Cola2 vs gpt-oss-20b
- Cola2 vs Granite 4.2 30B
- Cola2 vs Granite 4.2 3B
- Cola2 vs Granite 4.2 8B
- Cola2 vs Hy-Memory-30B-A3B
- Cola2 vs Hy3
- Cola2 vs Inkling
- Cola2 vs Inkling 2 Small
- Cola2 vs Inkling-Small
- Cola2 vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Cola2 vs Kimi K3
- Cola2 vs Kimi K3.1 Pro
- Cola2 vs Kolibri-1
- Cola2 vs Kronos
- Cola2 vs Laguna M.1
- Cola2 vs Laguna S 2.1
- Cola2 vs Laguna XS 2.1
- Cola2 vs LBS-27B
- Cola2 vs LFM2.5-2.6B
- Cola2 vs LFM3-1.7B
- Cola2 vs LFM3-Audio-2B
- Cola2 vs LFM3-Omni-2B
- Cola2 vs LFM3-VL-2B
- Cola2 vs Ling-3.0-tiny
- Cola2 vs Ling-3.1-flash-1019
- Cola2 vs LongCat-2.5
- Cola2 vs MiMo-V2.6 Distill Qwen 9B
- Cola2 vs MiMo-V2.6-Flash-RL
- Cola2 vs MiniCPM-o 4.5
- Cola2 vs MiniCPM-V 4.7 1B
- Cola2 vs MiniCPM-V 4.7 35B-A3B
- Cola2 vs MiniCPM5-2B
- Cola2 vs MiniMax-M2.5
- Cola2 vs MiniMax-M2.7
- Cola2 vs MiniMax-M3.1-Flash
- Cola2 vs Mistral Large 4
- Cola2 vs Muse Glimmer 30B
- Cola2 vs Nanbeige4.2-3B
- Cola2 vs Nanbeige4.3-33B
- Cola2 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Cola2 vs Nemotron 3.5 Lightning 30B A3B
- Cola2 vs Nemotron 3 Nano 30B A3B
- Cola2 vs Nemotron 3 Nano 4B
- Cola2 vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Cola2 vs Nemotron 3 Super 120B A12B
- Cola2 vs Nemotron 3 Ultra 550B A55B
- Cola2 vs North Mini Code 1.0
- Cola2 vs occamy-1.0
- Cola2 vs Olmo 3 7B Think
- Cola2 vs Ornith-1.5-122B
- Cola2 vs Ornith-1.5-35B-A3B
- Cola2 vs Ornith-1.5-397B
- Cola2 vs Ornith-1.5-9B
- Cola2 vs OTel-2.0-LLM-31B-IT
- Cola2 vs Qwen-AgentWorld-35B-A3B
- Cola2 vs Qwen3-30B-A3B-Instruct-2507
- Cola2 vs Qwen3-4B-Instruct-2507
- Cola2 vs Qwen3.5-0.8B
- Cola2 vs Qwen3.5-122B-A10B
- Cola2 vs Qwen3.5-2B
- Cola2 vs Qwen3.5-397B-A17B
- Cola2 vs Qwen3.5-4B
- Cola2 vs Qwen3.5-9B
- Cola2 vs Qwen3.6-27B
- Cola2 vs Qwen3.6-35B-A3B
- Cola2 vs Qwen3.8-27B
- Cola2 vs Qwen3.8-Flash-Next
- Cola2 vs Qwen3-Coder-30B-A3B-Instruct
- Cola2 vs Qwen3-Coder-Next
- Cola2 vs Qwen3-Omni-30B-A3B-Instruct
- Cola2 vs Qwen3-VL-2B-Instruct
- Cola2 vs Qwen3-VL-30B-A3B-Instruct
- Cola2 vs Qwen3-VL-32B-Instruct
- Cola2 vs Qwen3-VL-4B-Instruct
- Cola2 vs Qwen3-VL-8B-Instruct
- Cola2 vs Qwopus3.8-27B-Flash-V2
- Cola2 vs Recursive Flint
- Cola2 vs Ripple-65B Preview
- Cola2 vs SenseNova-Loop-9B-Preview
- Cola2 vs SmolLM3-3B
- Cola2 vs Spark-X2.6-4B
- Cola2 vs Step 3.7 Flash
- Cola2 vs Swift 1.5 Qwen3.8-27B
- Cola2 vs Swift 1.5 Qwen3.8-Flash-Next
- Cola2 vs ThinkingCap (Qwen3.8 27B)
- Cola2 vs Baidu Unlimited-OCR-2
- Cola2 vs WeVisOne-VL-2B
- Cola2 vs WeVisOne-VL-4B
- Cola2 vs ZAYA1-8B
- Cosmos-Reason2-2B vs Inkling 2 Mini
- Darwin-36B-Opus vs Inkling 2 Mini
- DeepSeek-V3.2 vs Inkling 2 Mini
- DeepSeek V4.1 Flash vs Inkling 2 Mini
- DeepSeek-V4-Flash-0731 vs Inkling 2 Mini
- Devstral Small 2 vs Inkling 2 Mini
- DiffusionGemma 26B A4B IT vs Inkling 2 Mini
- EXAONE 4.5 33B vs Inkling 2 Mini
- Gemma 4 12B IT vs Inkling 2 Mini
- Gemma 4 26B A4B IT vs Inkling 2 Mini
- Gemma 4 31B IT vs Inkling 2 Mini
- Gemma 4 E2B IT vs Inkling 2 Mini
- Gemma 4 E4B IT vs Inkling 2 Mini
- GLM-4.5-Air vs Inkling 2 Mini
- GLM-4.7-Flash vs Inkling 2 Mini
- GLM-5.3-Flash vs Inkling 2 Mini
- GLM-5.3 vs Inkling 2 Mini
- gpt-oss-120b vs Inkling 2 Mini
- gpt-oss-20b vs Inkling 2 Mini
- Granite 4.2 30B vs Inkling 2 Mini
- Granite 4.2 3B vs Inkling 2 Mini
- Granite 4.2 8B vs Inkling 2 Mini
- Hy-Memory-30B-A3B vs Inkling 2 Mini
- Hy3 vs Inkling 2 Mini
- 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/cola2-vs-inkling-2-mini.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/cola2.json·/api/v1/tools/inkling-2-mini.json - From a terminal
anchor compare cola2 inkling-2-mini(the CLI) - Over MCP
compare_tools {"a": "cola2", "b": "inkling-2-mini"}at/mcp, no key