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

Inkling 2 Mini vs ZAYA1-8B

Inkling 2 Mini and ZAYA1-8B score within a point of each other on agent readiness, 61 (C) and 61 (C). ZAYA1-8B 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

  • Risk, 70 against 55
  • Agent interface, 85 against 60
  • Documentation and upkeep, 57 against 50

Watch for

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

ZAYA1-8B C

Best for People who want a small, fast reasoning model for maths and code and can live without tool calling

Ahead on

  • Reach, 80 against 60

Watch for

Tool calling needs a parser that only Zyphra's vLLM fork has

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 +25

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.

ZAYA1-8B 60

Chat template 20, chat_template.jinja in the repository (10,700 characters). Tool-calling format 10, only the template and a fork say it. Trained tool calling 10, the template takes tools and renders calls, and the card recommends settings for agent use, but it doesn't say the model was trained for tool calling or for several calls in a turn, so the lower band. Structured output 0, Nothing on the card about JSON or schema-constrained output. Reasoning control 10, the template has an enable_thinking switch, and the card names the qwen3 reasoning parser, which returns the reasoning apart from the answer. Context 10, 131,072 positions in config.json, for an architecture Zyphra trained end to end, so the config is the model's own. 20 + 10 + 10 + 0 + 10 + 10 = 60.

Reach ZAYA1-8B +20

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.

ZAYA1-8B 80

Memory 30, the smallest build from Zyphra is the MXFP4-Experts repository, 5.85 GB, and 5.85 GB × 1.2 = 7.0 GB, within 16 GB. Runtimes 10, Released Transformers 5.22.2 has the zaya model and SGLang 0.5.23 has srt/models/zaya.py. Builds 15, Quantised builds from Zyphra at two precisions, FP8 and MXFP4 for the experts, each in its own repository. Terms 15, Apache 2.0 in the card's metadata, 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, and the card names no API. Zyphra's site lists a cloud product for its open models, which wasn't checked for this model. 30 + 10 + 15 + 15 + 10 + 0 = 80.

Risk Inkling 2 Mini +15

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.

ZAYA1-8B 55

File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, the files sit in the Zyphra organisation, which the card ties to zyphra.com's blog post for the model (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 0, no way to report a flaw on the card, and www.zyphra.com has no security.txt. 25 + 15 + 0 + 0 + 15 + 0 = 55.

Documentation and upkeep Inkling 2 Mini +7

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.

ZAYA1-8B 50

Model card 5, Intended use and the parameter counts are on the card. Training data 0, Nothing on the card about the training data. Last change 10, the main repository last changed on 26 June 2026 (the checkpoint reshaped for Transformers), 137 days before this check, and the quantised repositories on 2 July, 131 days. Responsiveness 20, Of the 16 most recent discussions that aren't pull requests (7 May to 14 August 2026), 10 have a reply from a Zyphra member, which is most. Version policy 5, the original checkpoint is kept as ZAYA1-8B-legacy and the card says so at the top, without a date. File health 10, Config, template and card agree on the architecture after the reshape. 5 + 0 + 10 + 20 + 5 + 10 = 50.

Score by category

CategoryWeightInkling 2 MiniZAYA1-8BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%6080ZAYA1-8B +20
Risk20%7055Inkling 2 Mini +15
Agent interface10%8560Inkling 2 Mini +25
Documentation and upkeep10%5750Inkling 2 Mini +7
Negative events≤1500
TotalC 61/100C 61/100

Facts side by side

FactInkling 2 MiniZAYA1-8B
KindOpen-weight modelOpen-weight model
VendorThinking Machines LabZyphra
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-11-202026-07-02
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked

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.

ZAYA1-8B

A small reasoning model trained from scratch by one lab, with a clean licence, 4-bit and FP8 builds and a team that answers questions. It's the hardest of the small models to run: its own architecture, a card that points at forks, and tool calling that needs a parser no release has. Little on limits, data or safety.

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

ZAYA1-8B

  1. Use it for reasoning, maths and code. Don't count on tool calling outside Zyphra's vLLM fork
  2. Run it with Transformers 5.22.2 or SGLang 0.5.23, which have the model built in
  3. Use temperature 1.0 and top_p 0.95 in general, and temperature 0.6 for agent and code work
  4. Download Zyphra/ZAYA1-8B, not the legacy repository, for the released runtimes
  5. The quantised repositories have no licence tag. The main one is Apache 2.0

Questions

Which is better for AI agents, Inkling 2 Mini or ZAYA1-8B?

Inkling 2 Mini and ZAYA1-8B score within a point of each other on agent readiness, 61 (C) and 61 (C). ZAYA1-8B leads on reach.

Other comparisons with Inkling 2 Mini or ZAYA1-8B

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.