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

Inkling 2 Mini vs Laguna M.1

Inkling 2 Mini scores 61 (C) on agent readiness against Laguna M.1's 56.7 (C), and leads in 2 of 4 scored categories. Laguna M.1 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

Inkling 2 Mini C

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 55
  • Documentation and upkeep, 57 against 36

Watch for

No released version of vLLM, SGLang, Transformers, llama.cpp or Ollama runs it on 20 November 2026

Laguna M.1 C

Best for Teams with a multi-GPU Blackwell or Hopper server that want a large coding agent model under Apache 2.0.

Ahead on

  • Reach, 70 against 60

Watch for

The smallest build needs about 167 GB, more than a 128 GB machine

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 Inkling 2 Mini +21

Inkling 2 Mini 57

Model card 17, no knowledge cut-off. Training data 5, a general description with no cut-off and no summary for this model yet. Last change 20, uploaded today. Responsiveness 0, two questions and none answered within the first hour. Version policy 5, a first release. File health 10, the files and the card agree. 17 + 5 + 20 + 0 + 5 + 10 = 57.

Laguna M.1 36

Model card 11 of 20, intended use, architecture, parameters and context are there, limitations, languages and a cut-off aren't. Training data 5, the report describes sources and filtering but gives no cut-off. Last change 10, 14 July 2026, 113 days ago. Responsiveness 0, the one discussion's only reply is from someone outside the poolside organisation. Version policy 5, a first open release with nothing replaced. File health 5, generation config and template disagree on the thinking default and the FP8 build's Docker files name different image tags.

Risk Inkling 2 Mini +15

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.

Laguna M.1 55

File safety 15 of 25, safetensors only, but the repository ships model code behind auto_map and the card's SGLang and TensorRT-LLM instructions use trust_remote_code. Provenance 15, the verified poolside organisation, with a checksum on every file. Safety evaluation 0, none published. Agent guidance 5, general cautions only. Licence risk 15, plain Apache 2.0. Security programme 5, a signed security.txt and a security contact on the card, with no public advisories found.

Reach Laguna M.1 +10

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.

Laguna M.1 70

Memory 5 of 30, the smallest 4-bit build is Poolside's 139.3 GB NVFP4, which needs 192 GB with a fifth added, beyond our reference machine. Runtimes 25, released llama.cpp, Ollama (through the llama.cpp release it pins), vLLM, SGLang and Transformers run the laguna architecture. Builds 15, FP8 and NVFP4 from Poolside. Terms 15, Apache 2.0 with nothing binding added. Download 10, nothing is gated. Hosted 0, no provider is mapped on the Hub and Poolside's API docs name only S 2.1.

Score by category

CategoryWeightInkling 2 MiniLaguna M.1Edge
Capability35%pendingpendingpendingnot scored in this run
Reach25%6070Laguna M.1 +10
Risk20%7055Inkling 2 Mini +15
Agent interface10%8585even
Documentation and upkeep10%5736Inkling 2 Mini +21
Negative events≤1500
TotalC 61/100C 56.7/100

Facts side by side

FactInkling 2 MiniLaguna M.1
KindOpen-weight modelOpen-weight model
VendorThinking Machines LabPoolside
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-11-202026-07-14
Terms last updatedno document linked2026-07-21
Privacy policy last updatedno document linked2026-07-21
Customer content may train modelsnot read yetyes, with an opt-out
Terms restrict automated accessnot read yetnot found in the text
Terms restrict benchmarkingnot read yetnot found in the text
Terms or service can change without noticenot read yetyes
Arbitration or class-action waivernot read yetyes
Agent reviewsnone2.5/5 (4)

How the scores have moved

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.

Laguna M.1

A large open-weight coding and agent model under plain Apache 2.0, for teams with a multi-GPU server. Its smallest build needs about 167 GB, more than a 128 GB machine. Released llama.cpp, Ollama, vLLM, SGLang and Transformers code runs the architecture. The files haven't changed since 14 July 2026, no hosted endpoint was found, and no safety results are published.

Before you call either

Inkling 2 Mini

  1. 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 is inkling2
  2. 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
  3. Pass reasoning_effort as 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
  4. The card says it can get stuck re-checking its own work, so cap output tokens and agent turns
  5. 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
  6. Tool call arguments must reach the template as an object, not a JSON string, as for Inkling 2 Small
  7. Images should be 40 to 4096 px a side. It takes no audio, and the template raises an error for an audio part
  8. Use guided decoding or validate JSON yourself, since structured output isn't documented
  9. Without the hardware, sample from it on Tinker with the Tinker SDK; Tinker's OpenAI-compatible endpoint doesn't serve it yet
  10. Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal

Laguna M.1

  1. Run the NVFP4 build on Blackwell GPUs with vllm serve poolside/Laguna-M.1-NVFP4 --tensor-parallel-size 2 --tool-call-parser poolside_v1 --reasoning-parser poolside_v1 --enable-auto-tool-choice, on vLLM 0.21.0 or later
  2. Thinking is off in the template unless you pass enable_thinking true or start the server with --default-chat-template-kwargs '{"enable_thinking": true}', which Poolside recommends for agentic coding
  3. Pass earlier reasoning back as reasoning_content in the history, since the card says reasoning may stop in later steps if it's dropped
  4. Sampling per the card is temperature 1.0 and top_k 20
  5. The FP8 build's Docker image and serve.sh predate upstream support and set a 4,096-token context, so prefer a released vLLM
  6. It doesn't fit our 128 GB reference machine at any published precision
  7. Validate JSON output yourself or use the runtime's guided decoding, since structured output isn't documented

Questions

Which is better for AI agents, Inkling 2 Mini or Laguna M.1?

Inkling 2 Mini scores 61 (C) on agent readiness against Laguna M.1's 56.7 (C), and leads in 2 of 4 scored categories. Laguna M.1 leads on reach.

Other comparisons with Inkling 2 Mini or Laguna M.1

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.