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

Inkling 2 Mini vs Qwen3.5-0.8B

Inkling 2 Mini scores 61 (C) on agent readiness against Qwen3.5-0.8B's 46.7 (D), and leads in 3 of 4 scored categories. Qwen3.5-0.8B 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 60
  • Documentation and upkeep, 57 against 37

Watch for

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

Qwen3.5-0.8B D

Best for Builders who want a near-free local helper or fine-tuning base for narrow tasks on a phone-class device, laptop or CPU

Ahead on

  • Reach, 80 against 60

Watch for

No quantised build from Alibaba and no inference provider found

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 +25

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.

Qwen3.5-0.8B 60

The template ships in the repository (20) and the model was trained for tool use with several calls per turn in the template (20). Tool-calling format gets 10, because the card names the qwen3_coder parser but leaves the format to the template. Reasoning control scores 0, since the card shows how to turn thinking on but not where the reasoning comes back. 262,144 tokens is native (10). Structured output scores 0, as nothing documents JSON output for the model. 20+10+20+0+0+10 = 60.

Reach Qwen3.5-0.8B +20

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.

Qwen3.5-0.8B 80

Memory earns the full 30, since LM Studio's Q4_K_M build with its projector is 0.73 GB (0.88 GB with the fifth added) and Ollama's Q8_0 build was 1.0 GB, both far within 16 GB. Alibaba publishes no quantised 0.8B, so builds scores 0. Runtimes reach the 25 cap on llama.cpp, Ollama (through its pinned llama.cpp), vLLM, SGLang, LM Studio and Transformers. Apache 2.0 with nothing added gives terms 15 and the ungated repository download 10. Hosted too scores 0, as the Hub maps no inference provider to this size. 30+25+0+15+10+0 = 80.

Documentation and upkeep Inkling 2 Mini +20

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.

Qwen3.5-0.8B 37

The card covers six of the seven items, missing only a cut-off (17), because it states the intended uses and warns about thinking loops. Training data is a general description without a cut-off (5). The files last changed on 2 March 2026, 248 days before this check, within a year (5). No Qwen member has answered any of the 15 discussions that aren't pull requests (0). Qwen3-0.6B stays in its own repository without a dated note (5), and a template fix and the missing generation_config.json wait unanswered (5). 17+5+5+0+5+5 = 37.

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.

Qwen3.5-0.8B 55

Safetensors only with no remote code gives file safety its 25, and files in the Qwen organisation the publisher's GitHub links to, each with a hash on the Hub, give provenance 15. The Apache 2.0 licence carries none of the deductions, so licence risk keeps 15. Safety evaluation, agent guidance and a security programme score 0, since the card has no safety results or agent cautions and no reporting route was found. The Qwen3.5 blog and Alibaba's security response centre couldn't be read, so those are scored as absent and left open. 25+15+0+0+15+0 = 55.

Score by category

CategoryWeightInkling 2 MiniQwen3.5-0.8BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%6080Qwen3.5-0.8B +20
Risk20%7055Inkling 2 Mini +15
Agent interface10%8560Inkling 2 Mini +25
Documentation and upkeep10%5737Inkling 2 Mini +20
Negative events≤1500
TotalC 61/100D 46.7/100

Facts side by side

FactInkling 2 MiniQwen3.5-0.8B
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 release2026-11-202026-03-02
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.

Qwen3.5-0.8B

A tiny vision-language model for prototypes, fine-tuning and narrow local steps such as routing, tagging or reading an image. It runs in about 1 GB at 4 or 8 bits in six runtimes under plain Apache 2.0. Keep thinking off, since the card warns it loops. The card has no safety results, and Qwen has answered none of its discussions.

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

Qwen3.5-0.8B

  1. Smallest start is ollama run qwen3.5:0.8b, or qwen3.5:0.8b-q8_0 at 1.0 GB
  2. Full precision vllm serve Qwen/Qwen3.5-0.8B --port 8000 --max-model-len 262144 --enable-auto-tool-choice --tool-call-parser qwen3_coder
  3. Thinking is off by default; if you turn it on with "chat_template_kwargs": {"enable_thinking": true}, stream and cut off runaway output, since the card warns of thinking loops, and add --reasoning-parser qwen3 in vLLM or SGLang to split the reasoning out
  4. There's no generation_config.json, so pass the card's sampling yourself, for example temperature=1.0, top_p=1.0, top_k=20, presence_penalty=2.0 for text without thinking
  5. Use it for narrow steps or as a fine-tuning base, not as the main agent, as the card itself suggests
  6. Validate any JSON it returns, since structured output isn't documented

Questions

Which is better for AI agents, Inkling 2 Mini or Qwen3.5-0.8B?

Inkling 2 Mini scores 61 (C) on agent readiness against Qwen3.5-0.8B's 46.7 (D), and leads in 3 of 4 scored categories. Qwen3.5-0.8B leads on reach.

Other comparisons with Inkling 2 Mini or Qwen3.5-0.8B

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.