Sign in

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

Inkling 2 Small vs Qwen3.8-27B

Qwen3.8-27B scores 68.6 (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 Qwen3.8-27BAlibaba (Qwen team) · Open-weight model B68.6/100#11 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 36

Watch for

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

Qwen3.8-27B B

Best for Agents that want a capable open model with vision on one 24 to 32 GB GPU or Mac, with the widest runtime support and a plain licence.

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 Qwen3.8-27B +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.

Qwen3.8-27B 90

Memory 25 of 30, Ollama's smallest 4-bit build is 18 GB, or 21.6 GB with a fifth added, which fits 24 GB. Runtimes 25, released versions of llama.cpp, Ollama, vLLM, SGLang 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, seven inference providers are live for it on Hugging Face on 1 November, though Qwen Cloud's own version is still described as coming soon.

Documentation and upkeep Inkling 2 Small +31

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.

Qwen3.8-27B 36

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 0, not described. Last change 15, the files last changed on 14 August 2026, 79 days before this check, and Qwen's GitHub repository for the model 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 27B models stay in their own repositories without dated notes. File health 5, the files agree with the card but reports about the template and structured output 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.

Qwen3.8-27B 70

Chat template 20, a Jinja file in the repository. Tool-calling format 10 of 25, the format lives only in the template and the parser name only in serving commands, Alibaba doesn't describe how tools are declared or returned. 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, reasoning_effort budgets it and the card shows the reasoning coming back in reasoning_content. 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.

Qwen3.8-27B 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 checksum. Safety evaluation 0, none published. 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, disclosure policy or security contact for Qwen 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 SmallQwen3.8-27BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%254090Qwen3.8-27B +50
Risk20%206555Inkling 2 Small +10
Agent interface10%108570Inkling 2 Small +15
Documentation and upkeep10%106736Inkling 2 Small +31
Negative events≤1500
TotalC 58.8/100B 68.6/100

Facts side by side

FactInkling 2 SmallQwen3.8-27B
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 release2026-11-122026-08-14
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

Qwen3.8-27B

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.

Qwen3.8-27B

A dense cousin for coding and agent work with image and video input that runs almost anywhere. Ollama's 4-bit build needs about 22 GB, and seven providers host it for agents without the hardware. The main risk is that nobody at Alibaba answers, there are no safety results or agent guidance, and the tool format is only in the template.

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

Qwen3.8-27B

  1. Quickest start is ollama run qwen3.8, about 18 GB of files
  2. On our reference machine use BF16 with vllm serve Qwen/Qwen3.8-27B --max-model-len 131072 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder, since FP8 on gfx1151 isn't documented
  3. Use the qwen3_coder tool parser, SGLang's cookbook says the Hermes parser leaves its calls unparsed
  4. Thinking is on by default, pass chat_template_kwargs with enable_thinking false for short tasks, and read the reasoning from reasoning_content
  5. reasoning_effort takes xhigh (default), medium or low, and any other value makes the template raise an error
  6. Sampling per the card is temperature 1.0 and top_p 0.95 when thinking, temperature 0.7, top_p 0.8 and presence_penalty 1.5 without
  7. Preserved thinking keeps earlier reasoning in the context unless preserve_thinking is false, which grows long agent sessions
  8. Turn on YaRN only beyond 262,144 tokens, the card warns static YaRN can cost quality on short texts
  9. 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 Small or Qwen3.8-27B?

Qwen3.8-27B scores 68.6 (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 Qwen3.8-27B

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