Sign in

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

Inkling-Small vs North Mini Code 1.0

Inkling-Small scores 67 (B) on agent readiness against North Mini Code 1.0's 61 (C), and leads in 2 of 4 scored categories. North Mini Code 1.0 leads on reach. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 6359 open weights comparisons

Inkling-SmallThinking Machines Lab · Open-weight model B67/100#13 of 160 open-weight models North Mini Code 1.0Cohere · Open-weight model C61/100#80 of 160 open-weight models

Which one, for what

Inkling-Small B

Best for Teams with 256 GB or more of datacentre GPU memory who want an open multimodal agent model with audio input and adjustable thinking.

Ahead on

  • Risk, 70 against 60
  • Documentation and upkeep, 87 against 36

Watch for

The smallest build Thinking Machines publishes needs about 205 GB

North Mini Code 1.0 C

Best for Developers who want a coding agent on their own GPU with a permissive licence

Ahead on

  • Reach, 85 against 55

Watch for

No limitations, safety results, languages or data description on the card

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-Small +51

Inkling-Small 87

Model card 17 of 20, everything but a dated knowledge cut-off, counting Thinking Machines' own model card page. Training data 15, an EU training-content summary with sources, mix, a July 2026 collection cut-off and filtering. Last change 20, the files last changed on 31 July 2026, but Thinking Machines' Inkling renderer in tinker-cookbook changed in its 30 October 2026 release. Responsiveness 20, Thinking Machines answered 8 of the 9 questions in its discussions. Version policy 5, a first release. File health 10, the files agree and no broken-file report waits. 17+15+20+20+5+10 = 87.

North Mini Code 1.0 36

Model card 11, Intended use, the architecture, the parameters and the context are on the card. Training data 0, the card gives the training method and nothing about the data. Last change 10, the main repository last changed on 15 June 2026 (outdated chat templates removed), 148 days before this check, and the draft model's repository on 29 July, 104 days. Responsiveness 0, none of the 11 most recent discussions that aren't pull requests (7 June to 6 November 2026) has a reply from a CohereLabs member, counted on 10 November by author flags and dates with a script, text not read. Version policy 5, A first release, with each build in its own repository. File health 10, Config, template and card agree on the architecture, and the June commit that removed broken templates says so. 11 + 0 + 10 + 0 + 5 + 10 = 36.

Reach North Mini Code 1.0 +30

Inkling-Small 55

Memory 5 of 30, the smallest 4-bit build is Thinking Machines' NVFP4 at 170.8 GB, about 205 GB with a fifth added, so it needs 256 GB. Runtimes 15, released Transformers, vLLM and SGLang run it, llama.cpp, Ollama and LM Studio don't. Builds 10, one quantised build (NVFP4). 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 serves it as beta serverless inference, and DeepInfra is live on Hugging Face.

North Mini Code 1.0 85

Memory 25, the smallest build from Cohere is the w4a16 repository, 19.38 GB, and 19.38 GB × 1.2 = 23.3 GB, within 24 GB. Unsloth's GGUF isn't read for this line. Runtimes 20, Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 have the cohere2_moe model, and llama.cpp b12242 has the cohere2moe architecture. Builds 15, Quantised builds from Cohere at two precisions, FP8 and 4-bit weights (w4a16), each in its own repository. Terms 15, Apache 2.0 in the metadata and on the card, an OSI licence with nothing added. Download 10, the Hub API reports gated false for the model and its builds on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it. 25 + 20 + 15 + 15 + 10 + 0 = 85.

Risk Inkling-Small +10

Inkling-Small 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 StrongREJECT and FORTRESS results and described external red-teaming, but nothing an outside party published or a harness to rerun. Agent guidance 10, the card says what its refusals miss and which safeguards to add, 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 programme 5, a security.txt and a disclosure policy, with public advisories unchecked and scored as absent.

North Mini Code 1.0 60

File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, the files sit in Cohere's verified CohereLabs organisation, which cohere.com links to per our other Cohere listings (10). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations or safety section, and nothing on prompt injection, instruction priority or what the model refuses. Licence risk 15, Apache 2.0 has no use policy, threshold or change clause. Security programme 5, Cohere's trust centre holds a responsible disclosure policy with a bug bounty, as recorded on our Cohere listings (5). 25 + 15 + 0 + 0 + 15 + 5 = 60.

Score by category

CategoryWeight this runInkling-SmallNorth Mini Code 1.0Edge
Capability35%pendingpendingpendingnot scored in this run
Reach25%255585North Mini Code 1.0 +30
Risk20%207060Inkling-Small +10
Agent interface10%108585even
Documentation and upkeep10%108736Inkling-Small +51
Negative events≤1500
TotalB 67/100C 61/100

Facts side by side

FactInkling-SmallNorth Mini Code 1.0
KindOpen-weight modelOpen-weight model
VendorThinking Machines LabCohere
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-07-312026-07-29
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviews3.5/5 (4)none

How the scores have moved

Inkling-Small

North Mini Code 1.0

No score change since it was listed.

Verdicts

Inkling-Small

A mixture-of-experts generalist with images and audio in, several tool calls a turn and per-request thinking effort. It needs about 205 GB for Thinking Machines' NVFP4 build on recent NVIDIA or AMD datacentre GPUs, and Tinker or DeepInfra host it. The main risks are a use policy that binds on download and can change, and no outside safety results.

North Mini Code 1.0

A coding agent model that fits one 24 GB GPU at 4 bits, trained for tool use, with a 256K context, Apache 2.0 and four released runtimes. It's a research release and reads like one: nothing on limitations, safety or data, the card's run instructions are out of date, and Cohere hasn't answered a question on the repository.

Before you call either

Inkling-Small

  1. Start the NVFP4 build with SGLang's recipe, sglang serve --trust-remote-code --model-path thinkingmachines/Inkling-Small-NVFP4 --tp 8 --enable-multimodal --reasoning-parser inkling --tool-call-parser inkling, on Blackwell for W4A4
  2. Use the inkling tool and reasoning parsers in vLLM or SGLang, or Thinking Machines' tml-renderers package to render prompts and parse calls yourself
  3. Pass reasoning_effort as none, minimal, low, medium, high (the default) or max, or a number from 0 to 0.99. The repository's template has no xhigh preset and raises an error for it, though Thinking Machines' docs and SGLang's cookbook list xhigh
  4. Effort none conditions the model toward no reasoning but doesn't forbid it, and higher effort needs a larger max_tokens
  5. Tool call arguments must reach the template as an object, not a JSON string, or it raises an error
  6. Images should be 40 to 4096 px a side and audio 16 kHz WAV under two minutes, per the card
  7. Use guided decoding or validate JSON yourself, since structured output isn't documented
  8. Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal

North Mini Code 1.0

  1. Serve it with vLLM 0.33.0 or later and --tool-call-parser cohere_command4 --reasoning-parser cohere_command4 --enable-auto-tool-choice, with cohere_melody installed
  2. Pass the model's thinking back with its tool calls on every turn. The card says results drop without it
  3. Describe tools in JSON schema and append tool results as a dictionary with the tool role
  4. Use temperature 1.0 and top_p 0.95
  5. For llama.cpp the GGUF files are Unsloth's or bartowski's conversions, not Cohere's
  6. It's text only. Don't send images

Questions

Which is better for AI agents, Inkling-Small or North Mini Code 1.0?

Inkling-Small scores 67 (B) on agent readiness against North Mini Code 1.0's 61 (C), and leads in 2 of 4 scored categories. North Mini Code 1.0 leads on reach.

Other comparisons with Inkling-Small or North Mini Code 1.0

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.

Get an auditSee a sample report