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

Inkling 2 Mini vs Qwen3-30B-A3B-Instruct-2507

Inkling 2 Mini scores 61 (C) on agent readiness against Qwen3-30B-A3B-Instruct-2507's 56.6 (C), and leads in 3 of 4 scored categories. Qwen3-30B-A3B-Instruct-2507 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
  • Agent interface, 85 against 75
  • Documentation and upkeep, 57 against 26

Watch for

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

Qwen3-30B-A3B-Instruct-2507 C

Best for Agents that want an instruct model with tool calling on one 24 GB GPU or a 32 GB Mac, with a plain licence and a 262,144-token context.

Ahead on

  • Reach, 90 against 60

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.

Documentation and upkeep Inkling 2 Mini +31

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.

Qwen3-30B-A3B-Instruct-2507 26

Model card 11 of 20, intended use, architecture, parameters and context are there, but limitations, named languages and a knowledge cut-off aren't. Training data 5, the cited Qwen3 report describes the data in general terms without a cut-off. Last change 0, the files and card last changed on 17 September 2025 (Hub lastModified on 4 November), and QwenLM/Qwen3's commits since are documentation only (the newest 8 January 2026). Responsiveness 0, counted by script on 4 November, with 32 discussions, 23 not pull requests (the newest 18 June 2026), and the only reply from a Qwen organisation member is Haihao's on discussion 3 (30 July 2025), who isn't counted as the publisher's staff (the ehartford and danielhanchen reading). Version policy 5, the older Qwen3-30B-A3B stays in its own repository without a note. File health 5, the files agree with the card but reports about the 1M mode wait without a reply. 11 + 5 + 0 + 0 + 5 + 5 = 26.

Reach Qwen3-30B-A3B-Instruct-2507 +30

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.

Qwen3-30B-A3B-Instruct-2507 90

Memory 25 of 30, LM Studio's MLX 4-bit build is 17.2 GB and Ollama's 4-bit build 19 GB, 21 to 23 GB with a fifth added, which fits 24 GB. Runtimes 25, released Transformers, vLLM, SGLang and llama.cpp run the qwen3_moe architecture, and Ollama's library and LM Studio's catalogue carry it. 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, Featherless AI on Hugging Face plus DekaLLM and SiliconFlow on OpenRouter serve it. On 4 November both repositories were still ungated with no file changed since 17 September 2025, and Featherless AI was still live in the Hub's provider mapping (OpenRouter's providers per 21 October). 25 + 25 + 10 + 15 + 10 + 5 = 90.

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.

Qwen3-30B-A3B-Instruct-2507 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, with a checksum on every file. Safety evaluation 0, none published. Agent guidance 0, nothing on prompt injection, refusals or safeguards. Licence risk 15, plain Apache 2.0 whose only change was the copyright year before release. 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. Files unchanged on 4 November, and QwenLM/Qwen3 still has no SECURITY.md. 25 + 15 + 0 + 0 + 15 + 0 = 55.

Agent interface Inkling 2 Mini +10

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.

Qwen3-30B-A3B-Instruct-2507 75

Chat template 20, a Jinja template in tokenizer_config.json. Tool-calling format 25, Qwen's own Function Calling guide documents the Hermes-style declaration and how calls come back, and names vLLM's hermes parser. Trained tool calling 20, the template allows one or more calls a turn. Structured output 0, not documented for the model, and Qwen's docs only point to vLLM's generic guided decoding. Reasoning control 0, this edition has no thinking. Context 10, 262,144 tokens native, with the 1M mode not counted. Template and config unchanged on 4 November. 20 + 25 + 20 + 0 + 0 + 10 = 75.

Score by category

CategoryWeightInkling 2 MiniQwen3-30B-A3B-Instruct-2507Edge
Capability35%pendingpendingpendingnot scored in this run
Reach25%6090Qwen3-30B-A3B-Instruct-2507 +30
Risk20%7055Inkling 2 Mini +15
Agent interface10%8575Inkling 2 Mini +10
Documentation and upkeep10%5726Inkling 2 Mini +31
Negative events≤1500
TotalC 61/100C 56.6/100

Facts side by side

FactInkling 2 MiniQwen3-30B-A3B-Instruct-2507
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 release2026-11-202025-09-17
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone2.8/5 (4)

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.

Qwen3-30B-A3B-Instruct-2507

A general-purpose instruct model with 3.3B of 30.5B parameters active per token, for instruction following, tool calling and long documents without a thinking step. It needs about 21 to 23 GB at 4 bits under Apache 2.0, and providers host it. Its files haven't changed in over a year, Alibaba hasn't answered its discussions, 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

Qwen3-30B-A3B-Instruct-2507

  1. Quickest start is ollama run qwen3:30b-instruct, 19 GB. Plain qwen3:30b and qwen3:30b-a3b are the Thinking-2507 edition, not this one
  2. On our reference machine use BF16 with vllm serve Qwen/Qwen3-30B-A3B-Instruct-2507 --max-model-len 262144 --enable-auto-tool-choice --tool-call-parser hermes, 61 GB of weights fits the GPU share
  3. Use the hermes parser in vLLM or qwen25 in SGLang, the template emits JSON inside tool_call tags
  4. Don't pass enable_thinking, this edition never thinks and the card says the flag isn't needed
  5. Sampling per the card is temperature 0.7, top_p 0.8, top_k 20 and min_p 0, with presence_penalty up to 2 against repetition
  6. Leave config.json as it is unless you need more than 262,144 tokens, the 1M mode swaps in config_1m.json and runs one sequence at a time
  7. Validate JSON 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 Qwen3-30B-A3B-Instruct-2507?

Inkling 2 Mini scores 61 (C) on agent readiness against Qwen3-30B-A3B-Instruct-2507's 56.6 (C), and leads in 3 of 4 scored categories. Qwen3-30B-A3B-Instruct-2507 leads on reach.

Other comparisons with Inkling 2 Mini or Qwen3-30B-A3B-Instruct-2507

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.