Sign in

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

Apertus v1.5 8B vs Inkling 2 Small

Apertus v1.5 8B scores 61 (C) on agent readiness against Inkling 2 Small's 58.8 (C), and leads in 2 of 4 scored categories. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 6472 open weights comparisons

Apertus v1.5 8BSwiss AI Initiative (EPFL and ETH Zurich) · Open-weight model C61/100#40 of 161 open-weight models Inkling 2 SmallThinking Machines Lab · Open-weight model C58.8/100#102 of 161 open-weight models

Which one, for what

Apertus v1.5 8B C

Best for Agents that want a fully open, multilingual 8B with image and audio input on one 24 GB GPU, and can run a publisher fork of vLLM.

Ahead on

  • Risk, 75 against 65
  • Documentation and upkeep, 84 against 67

Watch for

No released runtime supports it, only Swiss AI's forks of vLLM and Transformers

Inkling 2 Small C

Best for Teams with 512 GB or more of datacentre GPU memory who want Thinking Machines' newest open multimodal agent model and can run a runtime's pre-release image.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

The smaller checkpoint needs about 472 GB, and Thinking Machines says 500 GB of GPU memory

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 Apertus v1.5 8B +17

Apertus v1.5 8B 84

Model card 14 of 20, languages and a knowledge cut-off are missing. Training data 20, every dataset is public and listed with versions, licences and counts. Last change 20, the card changed on 14 October 2026, 20 days before 3 November, and Swiss AI added its own evaluation-results files on 26 October and 3 November. Responsiveness 20, Swiss AI answered all three questions, unchanged on 3 November 2026. Version policy 5, earlier models stay in their own repositories without a dated note. File health 5, the gated config couldn't be checked against the card, and the card and the policy disagree on the output filter.

Inkling 2 Small 67

Model card 17 of 20, everything but a dated knowledge cut-off. Training data 15, an EU training-content summary with sources, mix, an October 2026 collection cut-off and filtering. Last change 20, the files were uploaded on 12 November 2026. Responsiveness 0, the repository has no questions yet, which reads as none answered. Version policy 5, a first release. File health 10, the files agree and no broken-file report waits. 17 + 15 + 20 + 0 + 5 + 10 = 67.

Risk Apertus v1.5 8B +10

Apertus v1.5 8B 75

File safety 25, safetensors only and no code in the repository. Provenance 15, the files are in the swiss-ai organisation the report links, with a checksum on every file. Safety evaluation 10 of 20, published safety benchmarks run with Swiss AI's open harnesses and early access for three outside evaluators, but the manual evaluation is Swiss AI's own and can't be rerun. Agent guidance 10, the report says what the refusals cover, how far jailbreaks get and that capability limits are the main defence, with a personal-data filter to apply, but nothing on prompt injection for deployers. Licence risk 10, 5 off for the use policy. Security programme 5, ETH Zurich's disclosure policy, with no advisories found.

Inkling 2 Small 65

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, FORTRESS, HoneyBench and DistressBench results and described outside red-teaming, but nothing an outside party published or a harness to rerun. Agent guidance 5, the card names safeguards to add but doesn't say what its refusals cover, 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. 25 + 15 + 10 + 5 + 5 + 5 = 65.

Score by category

CategoryWeight this runApertus v1.5 8BInkling 2 SmallEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%254040even
Risk20%207565Apertus v1.5 8B +10
Agent interface10%108585even
Documentation and upkeep10%108467Apertus v1.5 8B +17
Negative events≤1500
TotalC 61/100C 58.8/100

Facts side by side

FactApertus v1.5 8BInkling 2 Small
KindOpen-weight modelOpen-weight model
VendorSwiss AI Initiative (EPFL and ETH Zurich)Thinking Machines Lab
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0, with the Apertus Acceptable Use Policy (v1.5, 14 July 2026) accepted at the download gateApache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-10-142026-11-12
Terms last updatednot read yetno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviews2.8/5 (4)none

How the scores have moved

Apertus v1.5 8B

No score change since it was listed.

Inkling 2 Small

Verdicts

Apertus v1.5 8B

A fully open 8B cousin, training data included, for multilingual chat and tool calls with images and audio in. It needs about 22 GB in BF16 and Swiss AI's own vLLM or Transformers fork, since no released runtime supports it. The main risks are a gated download with a policy to pass on and tools that fail with thinking on.

Inkling 2 Small

Thinking Machines' newest open model, a 594B mixture-of-experts generalist with images in, several tool calls a turn and per-request thinking effort. The NVFP4 checkpoint needs about 472 GB, and no released runtime runs it yet, so today that means vLLM's or SGLang's own images, or Tinker and Together hosted. The use policy binds on download and can change.

Before you call either

Apertus v1.5 8B

  1. Accept the terms on the card and set HF_TOKEN before downloading
  2. Use Swiss AI's Docker image ghcr.io/swiss-ai/vllm_apertus_1.5_release, since stock vLLM and Transformers don't load Apertus1p5ForConditionalGeneration yet
  3. Serve with --chat-template-content-format string --enable-auto-tool-choice --tool-call-parser apertus for tools, and leave thinking off when you need tools
  4. For thinking, set --reasoning-parser apertus and --default-chat-template-kwargs.enable_thinking true, and budget max tokens generously
  5. Audio is resampled to 24 kHz and costs 40 tokens a second, and video must be passed as frames
  6. Don't cast the loaded model with .half(), the image and audio tokenizers must stay in F32
  7. If you redistribute the weights, the policy says you must pass it on and get the recipient's express assent

Inkling 2 Small

  1. No released runtime runs it yet. Serve the NVFP4 checkpoint from SGLang's dev-inkling-2-small image with the cookbook's recipe for your hardware, or from vLLM's vllm/vllm-openai:inkling-2-small image
  2. In vLLM pass --reasoning-parser inkling --enable-auto-tool-choice --tool-call-parser inkling. In SGLang the tool-call parser is inkling2 and the reasoning parser inkling
  3. Transformers' main branch loads only thinkingmachines/Inkling-2-Small-MXFP8, the 622.8 GB checkpoint, and no release has the code yet
  4. Pass reasoning_effort as none, minimal, low, medium, high (the default), xhigh or max, or a number from 0 to 0.99
  5. Effort none conditions the model toward no reasoning but doesn't forbid it, and higher effort needs a larger max_tokens
  6. Tool call arguments must reach the template as an object, not a JSON string, or it raises an error
  7. Images should be 40 to 4096 px a side. The model 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, call it on Tinker's OpenAI-compatible endpoint with a Tinker key, at $0.30 input and $1.00 output per million tokens as read on 6 November 2026
  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, Apertus v1.5 8B or Inkling 2 Small?

Apertus v1.5 8B scores 61 (C) on agent readiness against Inkling 2 Small's 58.8 (C), and leads in 2 of 4 scored categories.

Other comparisons with Apertus v1.5 8B or Inkling 2 Small

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