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

Carbon-X vs Inkling 2 Mini

Carbon-X and Inkling 2 Mini score within a point of each other on agent readiness, 61 (C) and 61 (C). Inkling 2 Mini leads on risk and agent interface. 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

Carbon-X C

Best for Agents that need a second opinion on DNA variants and regulatory regions on a 16 to 24 GB machine, without sending sequences to a hosted model.

Ahead on

  • Reach, 90 against 60
  • Documentation and upkeep, 72 against 57

Watch for

Not clinically validated and no wet-lab validation reported

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 65
  • Agent interface, 85 against 35

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 +50

Carbon-X 35

Chat template 20, a Jinja file in the repository. Tool-calling format 10, only the inherited template shows the format and no parser is named. Trained tool calling 0, nothing says it was trained to call tools. Structured output 0, not documented. Reasoning control 0, thinking can be switched off but was never trained, and the card asks you to keep it off. Context 5, 40,960 tokens from the base, though Hugging Face trained at 8,192 and under 16K. Most of what the card documents for agents is Carbon-X as a tool another model calls, which this checklist doesn't read.

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.

Reach Carbon-X +30

Carbon-X 90

Memory 30, the publisher's Q4_K_M GGUF is 9.6 GB, or 11.6 GB with a fifth added. Runtimes 20, released llama.cpp (from b11742, which added the DNA tokeniser), vLLM, SGLang and Transformers all run it, with no Ollama or LM Studio entry. Builds 15, Hugging Face publishes GGUFs at four precisions. Terms 15, Apache 2.0 on the model and on its Qwen3-14B base. Download 10, nothing is gated. Hosted 0, no inference provider or Hugging Face API serves it.

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.

Documentation and upkeep Carbon-X +15

Carbon-X 72

Model card 17, everything but a knowledge cut-off. Training data 15, the mid-training sources and shares are listed, the instruction and fine-tuning data aren't named, and there's no cut-off. Last change 20, 28 October 2026, when config.json, generation_config.json, tokenizer_config.json and tokenizer.py were fixed. Responsiveness 10, organisation members replied to 2 of the 4 questions so far. Version policy 5, a first release whose history was squashed without a note. File health 5, the card now sends llama.cpp users to the publisher's GGUF repository, but the tokeniser config's 131,072 still contradicts the card's 40,960. 17 + 15 + 20 + 10 + 5 + 5 = 72.

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 +5

Carbon-X 65

File safety 15, safetensors and GGUF only, but the documented loading path runs the repository's tokenizer.py through trust_remote_code. Provenance 15, the files are in HuggingFaceBio, which Hugging Face's GitHub repository links, with a checksum on every file. Safety evaluation 10, Hugging Face reports its own dual-use check on sequence editing in the launch post, without numbers or a harness. Agent guidance 5, general cautions only. Licence risk 15, plain Apache 2.0. Security programme 5, Hugging Face's security.txt is a reporting route, and public advisories couldn't be checked.

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.

Score by category

CategoryWeightCarbon-XInkling 2 MiniEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%9060Carbon-X +30
Risk20%6570Inkling 2 Mini +5
Agent interface10%3585Inkling 2 Mini +50
Documentation and upkeep10%7257Carbon-X +15
Negative events≤1500
TotalC 61/100C 61/100

Facts side by side

FactCarbon-XInkling 2 Mini
KindOpen-weight modelOpen-weight model
VendorHugging Face (HuggingFaceBio)Thinking Machines Lab
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-10-282026-11-20
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviews3/5 (4)none

How the scores have moved

Verdicts

Carbon-X

A DNA specialist cousin that another agent calls for variant-effect and sequence questions, with DNA kept on the machine. Hugging Face's Q4_K_M GGUF needs about 12 GB and Q8_0 about 19 GB, on llama.cpp b11742 or later. It isn't clinically validated, isn't trained for tool calls or reasoning, and its Python tokeniser runs repository code.

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

Carbon-X

  1. Quickest start is llama-server -hf HuggingFaceBio/Carbon-X-GGUF:Q8_0 -ngl 99 -c 40960 --jinja --chat-template-kwargs '{"enable_thinking": false}' --temp 0.6 --top-p 0.95 --top-k 20 --min-p 0, on llama.cpp b11742 or later
  2. With vLLM or Transformers pass trust_remote_code, and expect the tokeniser to fetch Qwen/Qwen3-4B-Base at a pinned revision on first load
  3. Keep enable_thinking false and the card's sampling (temperature 0.6, top_p 0.95, top_k 20), the settings every reported result used
  4. Keep DNA in files and pass sequences by name, compute positions and base changes in code and send them as context, the card says the model miscounts long sequences
  5. Only A, C, G and T form 6-mers, so filter N and other IUPAC codes first or they become a single oov token
  6. Strip the dna tags from answers if you need bare sequence, llama.cpp keeps them in the text
  7. Cap max_tokens for next-base questions, long DNA generation is slow and degrades

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, Carbon-X or Inkling 2 Mini?

Carbon-X and Inkling 2 Mini score within a point of each other on agent readiness, 61 (C) and 61 (C). Inkling 2 Mini leads on risk and agent interface.

Other comparisons with Carbon-X 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.