Sign in

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

Inkling 2 Small vs Qwen3.6-27B

Qwen3.6-27B scores 66.7 (B) on agent readiness against Inkling 2 Small's 58.8 (C), and leads in 1 of 4 scored categories. Inkling 2 Small leads on risk, 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 6472 open weights comparisons

Inkling 2 SmallThinking Machines Lab · Open-weight model C58.8/100#102 of 161 open-weight models Qwen3.6-27BAlibaba (Qwen team) · Open-weight model B66.7/100#16 of 161 open-weight models

Which one, for what

Inkling 2 Small C

Best for Teams with 512 GB or more of datacentre GPU memory who want Thinking Machines' newest open multimodal agent model and can run a runtime's pre-release image.

Ahead on

  • Risk, 65 against 55
  • Agent interface, 85 against 70
  • Documentation and upkeep, 67 against 31

Watch for

The smaller checkpoint needs about 472 GB, and Thinking Machines says 500 GB of GPU memory

Qwen3.6-27B B

Best for Agents that want an open coding and tool-calling model with vision on one 24 to 32 GB GPU or Mac, with plain licence terms.

Ahead on

  • Reach, 90 against 40

Watch for

No safety results, prompt-injection guidance or security contact

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 Qwen3.6-27B +50

Inkling 2 Small 40

Memory 0 of 30, the smallest build is Thinking Machines' NVFP4 checkpoint at 393.5 GB, about 472 GB with a fifth added, above the 256 GB line. Runtimes 0, no released version of the six runs it; vLLM and SGLang serve it from their own images and Transformers has it on its main branch only. Builds 15, two precisions from the publisher (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 serves it as beta serverless inference, and Together is live on Hugging Face. 0 + 0 + 15 + 10 + 10 + 5 = 40.

Qwen3.6-27B 90

Memory 25 of 30, Ollama's text-only 4-bit build is 17 GB and the vision build 18 GB, about 20 to 22 GB with a fifth added, which fits 24 GB. Runtimes 25, released versions of llama.cpp, Ollama, vLLM, SGLang, LM Studio and Transformers all run the qwen3_5 architecture. Builds 10 of 15, Alibaba's only quantised build is FP8. Terms 15, Apache 2.0 with nothing added. Download 10, neither repository is gated. Hosted 5, three inference providers are live on Hugging Face and Alibaba's Model Studio serves it per the card.

Documentation and upkeep Inkling 2 Small +36

Inkling 2 Small 67

Model card 17 of 20, everything but a dated knowledge cut-off. Training data 15, an EU training-content summary with sources, mix, an October 2026 collection cut-off and filtering. Last change 20, the files were uploaded on 12 November 2026. Responsiveness 0, the repository has no questions yet, which reads as none answered. Version policy 5, a first release. File health 10, the files agree and no broken-file report waits. 17 + 15 + 20 + 0 + 5 + 10 = 67.

Qwen3.6-27B 31

Model card 11 of 20, intended use, architecture, parameters and context are there, but limitations, languages and a knowledge cut-off aren't. Training data 5, only a general family description without a cut-off, in the GitHub README. Last change 5, the files last changed on 24 April 2026, 191 days before this check, and Qwen's GitHub repository holds only a README and licence, so no reference code of Alibaba's changed later. Responsiveness 0, Qwen answered none of the 40 most recent questions and reports, recounted on 1 November. Version policy 5, earlier and later 27B models stay in their own repositories without dated notes. File health 5, the files agree with the card but template and tool-calling reports wait without a reply.

Agent interface Inkling 2 Small +15

Inkling 2 Small 85

Chat template 20, a Jinja file in the repository. Tool-calling format 25, Thinking Machines' tml-renderers guide shows how tools are declared and how calls come back for this model, and its package ships the parser. Trained tool calling 20, several calls in one turn. Structured output 0, not documented. Reasoning control 10, thinking effort is set per request from none to xhigh, and the reasoning comes back in reasoning_content. Context 10, up to 1M tokens. 20 + 25 + 20 + 0 + 10 + 10 = 85.

Qwen3.6-27B 70

Chat template 20, a Jinja file in the repository. Tool-calling format 10 of 25, the card names the qwen3_coder parser but the declaration and call format live only in the template. Trained tool calling 20, the template renders several calls in one turn. Structured output 0, not documented. Reasoning control 10, thinking turns off per request and comes back in think tags split out by the qwen3 parser. Context 10, 262,144 tokens native.

Risk Inkling 2 Small +10

Inkling 2 Small 65

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 StrongREJECT, FORTRESS, HoneyBench and DistressBench results and described outside red-teaming, but nothing an outside party published or a harness to rerun. Agent guidance 5, the card names safeguards to add but doesn't say what its refusals cover, 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 programme 5, a security.txt and a disclosure policy, with public advisories unchecked and scored as absent. 25 + 15 + 10 + 5 + 5 + 5 = 65.

Qwen3.6-27B 55

File safety 25, safetensors only and nothing from the repository runs to load it or build prompts. Provenance 15, the files are in the Qwen organisation that Qwen's GitHub links to, and every file has a hash on the Hub. Safety evaluation 0, none published on the card or README. Agent guidance 0, nothing on prompt injection, refusals or safeguards. Licence risk 15, plain Apache 2.0 that hasn't changed. Security programme 0, no security.txt, SECURITY.md or reporting route was found, and Alibaba's group security centre couldn't be checked, so it's scored as absent.

Score by category

CategoryWeight this runInkling 2 SmallQwen3.6-27BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%254090Qwen3.6-27B +50
Risk20%206555Inkling 2 Small +10
Agent interface10%108570Inkling 2 Small +15
Documentation and upkeep10%106731Inkling 2 Small +36
Negative events≤1500
TotalC 58.8/100B 66.7/100

Facts side by side

FactInkling 2 SmallQwen3.6-27B
KindOpen-weight modelOpen-weight model
VendorThinking Machines LabAlibaba (Qwen team)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-11-122026-04-22
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone3/5 (4)

How the scores have moved

Inkling 2 Small

Qwen3.6-27B

Verdicts

Inkling 2 Small

Thinking Machines' newest open model, a 594B mixture-of-experts generalist with images in, several tool calls a turn and per-request thinking effort. The NVFP4 checkpoint needs about 472 GB, and no released runtime runs it yet, so today that means vLLM's or SGLang's own images, or Tinker and Together hosted. The use policy binds on download and can change.

Qwen3.6-27B

A capable dense cousin for agentic coding and tool calls with images and video in, running in every major runtime. Ollama's 4-bit build needs about 22 GB, and three providers host it. The main risk is silence, with no safety results, no agent guidance, no answers in its repository and Qwen3.8-27B now ahead of it.

Before you call either

Inkling 2 Small

  1. No released runtime runs it yet. Serve the NVFP4 checkpoint from SGLang's dev-inkling-2-small image with the cookbook's recipe for your hardware, or from vLLM's vllm/vllm-openai:inkling-2-small image
  2. In vLLM pass --reasoning-parser inkling --enable-auto-tool-choice --tool-call-parser inkling. In SGLang the tool-call parser is inkling2 and the reasoning parser inkling
  3. Transformers' main branch loads only thinkingmachines/Inkling-2-Small-MXFP8, the 622.8 GB checkpoint, and no release has the code yet
  4. Pass reasoning_effort as none, minimal, low, medium, high (the default), xhigh or max, or a number from 0 to 0.99
  5. Effort none conditions the model toward no reasoning but doesn't forbid it, and higher effort needs a larger max_tokens
  6. Tool call arguments must reach the template as an object, not a JSON string, or it raises an error
  7. Images should be 40 to 4096 px a side. The model 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, call it on Tinker's OpenAI-compatible endpoint with a Tinker key, at $0.30 input and $1.00 output per million tokens as read on 6 November 2026
  10. Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal

Qwen3.6-27B

  1. Quickest start is ollama run qwen3.6:27b, about 18 GB of files with the vision projector
  2. Alibaba's FP8 build with the card's parsers is vllm serve Qwen/Qwen3.6-27B-FP8 --max-model-len 262144 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder, vllm 0.19.0 or later
  3. Use the qwen3_coder tool parser, the template writes calls as function and parameter blocks inside tool_call
  4. Thinking is on by default, pass "chat_template_kwargs": {"enable_thinking": false} for short tasks, and /think and /nothink aren't supported
  5. "preserve_thinking": true in chat_template_kwargs keeps earlier reasoning in context, which helps long agent sessions but grows the prompt
  6. Sampling per the card is temperature 1.0, top_p 0.95, top_k 20 when thinking, and temperature 0.7, top_p 0.8, presence_penalty 1.5 without
  7. Keep at least 128K of context if you rely on thinking, and turn on YaRN only beyond 262,144 tokens
  8. Validate any JSON it returns or use the runtime's guided decoding, since structured output isn't documented
  9. Qwen3.8-27B (listed as qwen3-8-27b) is the newer model at this size on the same runtimes

Questions

Which is better for AI agents, Inkling 2 Small or Qwen3.6-27B?

Qwen3.6-27B scores 66.7 (B) on agent readiness against Inkling 2 Small's 58.8 (C), and leads in 1 of 4 scored categories. Inkling 2 Small leads on risk, agent interface and documentation and upkeep.

Other comparisons with Inkling 2 Small or Qwen3.6-27B

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.

Get an auditSee a sample report