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

Cosmos-Reason2-2B vs Inkling 2 Mini

Inkling 2 Mini scores 61 (C) on agent readiness against Cosmos-Reason2-2B's 59.5 (C), and leads in 3 of 4 scored categories. Cosmos-Reason2-2B 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

Cosmos-Reason2-2B C

Best for Agents that need a small local model to reason over camera footage and images for robotics, driving or smart spaces

Ahead on

  • Reach, 65 against 60

Watch for

Gated behind a click-through licence that needs a Hugging Face account

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 60
  • Agent interface, 85 against 65
  • Documentation and upkeep, 57 against 39

Watch for

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

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 +20

Cosmos-Reason2-2B 65

A Jinja template ships as chat_template.json (20). Tools are declared only by the template it inherits from Qwen3-VL, with no NVIDIA documentation or parser (10), and nothing shows the 2B was trained for tool use (0). NVIDIA's prompt files ask for JSON with named keys for boxes, events and trajectories (15). Reasoning is asked for in the prompt and vLLM's qwen3 parser returns it apart (10). The card states 256K input tokens (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.

Documentation and upkeep Inkling 2 Mini +18

Cosmos-Reason2-2B 39

The card misses languages and a cut-off (14). Training data is named by dataset without sizes or a cut-off (5). The Hub repository last changed on 30 April 2026, 188 days before this check, which alone gives 5. NVIDIA's GitHub repository last changed with a README redirect to Cosmos 3 on 7 June 2026, 150 days back, and this run counts the publisher's documentation commits on this line (10). None of its 3 discussions has an NVIDIA reply, counted by author flags on 4 November (0). The 2B's weights were replaced in place in March with a dated line, and the family is now superseded by Cosmos 3 with a dated note (5). The gated files couldn't be checked against the card, which itself mixes float16 and BF16 and links a newer licence than the gate shows (5). 14 + 5 + 10 + 0 + 5 + 5 = 39.

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.

Risk Inkling 2 Mini +10

Cosmos-Reason2-2B 60

File safety gets the full 25, one safetensors file loaded by Transformers' own code with a template, no remote code. Provenance gets 15 for files in NVIDIA's own organisation with hashes. The licence has a use policy and guardrail clause and NVIDIA can revoke or update it, so licence risk keeps 5 of 15. NVIDIA's PSIRT route and bulletins give the security programme 10. Agent guidance gets 5 for general cautions about guardrails and physical risk, and safety evaluation 0, with no safety results.

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.

Reach Cosmos-Reason2-2B +5

Cosmos-Reason2-2B 65

Memory earns the full 30 because the BF16 file is 4.9 GB, about 5.9 GB with the fifth added, though NVIDIA itself asks for 24 GB of GPU memory. Runtimes get 20 because the model keeps Qwen3-VL's architecture, which Transformers, vLLM, SGLang and llama.cpp run in released versions, while LM Studio's catalogue has only the base. Builds score 0, as NVIDIA publishes no quantised build of the 2B. The NVIDIA Open Model License allows free commercial use under a use policy (10). The gate is an automatic click-through that needs an account (5), and nothing hosts the 2B (0).

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.

Score by category

CategoryWeightCosmos-Reason2-2BInkling 2 MiniEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%6560Cosmos-Reason2-2B +5
Risk20%6070Inkling 2 Mini +10
Agent interface10%6585Inkling 2 Mini +20
Documentation and upkeep10%3957Inkling 2 Mini +18
Negative events≤1500
TotalC 59.5/100C 61/100

Facts side by side

FactCosmos-Reason2-2BInkling 2 Mini
KindOpen-weight modelOpen-weight model
VendorNVIDIAThinking Machines Lab
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceNVIDIA Open Model License (custom, commercial use allowed, not an OSI licence); built on Qwen3-VL-2B-Instruct under Apache 2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-03-102026-11-20
Terms last updated2025-10-24no document linked
Privacy policy last updatedno document linkedno document linked
Customer content may train modelsyesnot read yet
Terms restrict automated accessnot found in the textnot read yet
Terms restrict benchmarkingnot found in the textnot read yet
Terms or service can change without noticenot found in the textnot read yet
Arbitration or class-action waivernot found in the textnot read yet
Agent reviews2.5/5 (4)none

Verdicts

Cosmos-Reason2-2B

A small local model for reasoning over video and images in robotics, driving and warehouse scenes, returning points, boxes and timed events as JSON. The 4.9 GB file runs in Transformers or vLLM, though NVIDIA asks for 24 GB of GPU memory. Development has moved to Cosmos 3, and the gated licence is revocable.

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.

Before you call either

Cosmos-Reason2-2B

  1. Accept the licence on the Hugging Face card with a signed-in account and set HF_TOKEN before downloading
  2. Serve it with vllm serve nvidia/Cosmos-Reason2-2B --max-model-len 16384 --media-io-kwargs '{"video": {"num_frames": -1}}' --reasoning-parser qwen3, keeping max-model-len between 8,192 and 16,384 as NVIDIA advises
  3. For local video or images, make a folder for them (mkdir -p media) and pass --allowed-local-media-path "$(pwd)/media", so the server can read only that folder, not everything under the directory you start it from
  4. Sample video at 4 fps and allow at least 4,096 output tokens so the reasoning isn't cut off
  5. For reasoning, add the card's instruction to answer with a think block and then the answer; leave it out for a direct reply
  6. Use NVIDIA's prompt files (prompts/*.yaml in nvidia-cosmos/cosmos-reason2) when you want JSON boxes, events or trajectories, and validate the JSON yourself
  7. Check its plans before a robot acts on them, since NVIDIA's own safety card warns of collision and manipulation risks

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

Questions

Which is better for AI agents, Cosmos-Reason2-2B or Inkling 2 Mini?

Inkling 2 Mini scores 61 (C) on agent readiness against Cosmos-Reason2-2B's 59.5 (C), and leads in 3 of 4 scored categories. Cosmos-Reason2-2B leads on reach.

Other comparisons with Cosmos-Reason2-2B or Inkling 2 Mini

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.