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

Inkling 2 Mini vs Nemotron 3 Ultra 550B A55B

Nemotron 3 Ultra 550B A55B scores 69.3 (B) on agent readiness against Inkling 2 Mini's 61 (C), and leads in 2 of 4 scored categories. Inkling 2 Mini 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

  • Reach, 60 against 55

Watch for

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

Nemotron 3 Ultra 550B A55B B

Best for Agents with a multi-GPU Blackwell or Hopper node, or using a hosted endpoint, that want NVIDIA's strongest open model for long agent runs

Ahead on

  • Agent interface, 90 against 85
  • Documentation and upkeep, 70 against 57

Watch for

The smallest build is 352 GB and needs at least four B200-class GPUs

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 Nemotron 3 Ultra 550B A55B +13

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.

Nemotron 3 Ultra 550B A55B 70

The model card earns 20, all seven items with limitations in the linked subcard. Training data earns 20, datasets listed with sources and token counts, cut-offs and filtering, and the corpora published. Last change earns 20, counting NVIDIA's own inference code for the model. The repositories last changed on 24 August, but NVIDIA's TensorRT-LLM, the runtime the card's own serving commands use, changed its Nemotron-H model code on 14 October, 18 days ago. Responsiveness earns 0, with no NVIDIA reply to any of nine questions. Version policy earns 5 as a first release. File health earns 5, since there is no LICENSE file, the BF16 card's SGLang command names a parser SGLang doesn't have, and tool-call reports wait without a reply.

Reach Inkling 2 Mini +5

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.

Nemotron 3 Ultra 550B A55B 55

Memory earns 0, because the smallest 4-bit build, NVIDIA's 352 GB NVFP4, needs about 423 GB with the fifth added, above the 256 GB band, and no runtime library has a local build. Runtimes earn 20 from released vLLM, SGLang, llama.cpp and Transformers, with Ollama's cloud-only entry not counted. Builds earn 10 for the single NVFP4 build. Terms earn 10, because OpenMDW-1.1 is permissive with no threshold or use policy but isn't an OSI licence. Download earns 10, with no gate or account. Hosted earns 5, since NVIDIA's own API serves it and two providers host it.

Agent interface Nemotron 3 Ultra 550B A55B +5

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.

Nemotron 3 Ultra 550B A55B 90

The chat template earns 20, a Jinja file in the repository. The tool-calling format earns 25, since the card names the qwen3_coder parser and shows a tool call declared and read back. Trained tool calling earns 20, with tool-use training and several calls per turn in the template. Structured output earns 5, claimed from training with no instructions. Reasoning control earns 10, thinking off or medium effort per request with a runtime parser that returns the reasoning apart. Context earns 10 for up to 1M tokens.

Score by category

CategoryWeightInkling 2 MiniNemotron 3 Ultra 550B A55BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%6055Inkling 2 Mini +5
Risk20%7070even
Agent interface10%8590Nemotron 3 Ultra 550B A55B +5
Documentation and upkeep10%5770Nemotron 3 Ultra 550B A55B +13
Negative events≤1500
TotalC 61/100B 69.3/100

Facts side by side

FactInkling 2 MiniNemotron 3 Ultra 550B A55B
KindOpen-weight modelOpen-weight model
VendorThinking Machines LabNVIDIA
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0OpenMDW-1.1
Read-only variant documentednono
llms.txtnono
Last release2026-11-202026-06-04
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone2.8/5 (4)

How the scores have moved

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.

Nemotron 3 Ultra 550B A55B

NVIDIA's frontier-scale agent cousin with trained parallel tool calls, up to a 1M-token context and training against prompt injection through tool output. It needs at least four Blackwell GPUs for the 352 GB NVFP4 build, so most agents will use NVIDIA's API or a provider. The main risks are serving commands that run repository code and no published safety results.

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

Nemotron 3 Ultra 550B A55B

  1. It doesn't fit the 128 GB reference machine at any precision. Call NVIDIA's API (model nvidia/nemotron-3-ultra-550b-a55b) or a provider instead
  2. With vLLM serve the NVFP4 build with --trust-remote-code --reasoning-parser nemotron_v3 --enable-auto-tool-choice --tool-call-parser qwen3_coder on 4 × B200 or more
  3. With SGLang use --reasoning-parser nemotron_3, not the BF16 card's nemotron_v3, which SGLang doesn't register
  4. On SGLang with tools, pass chat_template_kwargs with enable_thinking true and force_nonempty_content true, as the card says, or reasoning and calls won't both parse
  5. Thinking is on by default. Pass enable_thinking: false for short tasks or medium_effort: true to cut reasoning tokens
  6. Use temperature=1.0 and top_p=0.95, as the generation config sets

Questions

Which is better for AI agents, Inkling 2 Mini or Nemotron 3 Ultra 550B A55B?

Nemotron 3 Ultra 550B A55B scores 69.3 (B) on agent readiness against Inkling 2 Mini's 61 (C), and leads in 2 of 4 scored categories. Inkling 2 Mini leads on reach.

Other comparisons with Inkling 2 Mini or Nemotron 3 Ultra 550B A55B

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.