Sign in

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

BigBang-v1 vs Inkling 2 Small

Inkling 2 Small scores 58.8 (C) on agent readiness against BigBang-v1's 56.3 (C), and leads in 3 of 4 scored categories. BigBang-v1 leads on reach. 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

BigBang-v1The Endless Frontier (endless-frontier) · Open-weight model C56.3/100#117 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

BigBang-v1 C

Best for Agents with 96 GB or more that want an Apache 2.0 mixture-of-experts model tuned for research, search and coding, and can do without publisher support.

Ahead on

  • Reach, 60 against 40

Watch for

BF16 is the only build from the publisher, needing about 86 GB

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.

Ahead on

  • Risk, 65 against 55
  • Agent interface, 85 against 60
  • Documentation and upkeep, 67 against 46

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.

Agent interface Inkling 2 Small +25

BigBang-v1 60

Chat template 20, the base's template in the repository. Tool-calling format 10 of 25, the card names the qwen3_coder parser and nothing more. Trained tool calling 20, tuned for tool use with several calls a turn. Structured output 0. Reasoning control 0, the card doesn't say how to turn thinking off or budget it. Context 10, 262,144 tokens. 20 + 10 + 20 + 0 + 0 + 10 = 60.

Inkling 2 Small 85

Chat template 20, a Jinja file in the repository. Tool-calling format 25, Thinking Machines' tml-renderers guide shows how tools are declared and how calls come back for this model, and its package ships the parser. Trained tool calling 20, several calls in one turn. Structured output 0, not documented. Reasoning control 10, thinking effort is set per request from none to xhigh, and the reasoning comes back in reasoning_content. Context 10, up to 1M tokens. 20 + 25 + 20 + 0 + 10 + 10 = 85.

Documentation and upkeep Inkling 2 Small +21

BigBang-v1 46

Model card 11 of 20, limitations, architecture and a cut-off are missing. Training data 5, a general description of about 10,000 synthetic examples. Last change 15, the card last changed on 6 August 2026, 90 days before this check. Responsiveness 0, no publisher reply to any of 7 questions. Version policy 5, a first release. File health 10, the files agree with the card and the base. 11 + 5 + 15 + 0 + 5 + 10 = 46.

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.

Reach BigBang-v1 +20

BigBang-v1 60

Memory 10 of 30, the only build from the publisher is BF16 at 71.9 GB, 86.3 GB with a fifth added, which fits the reference machine but not 64 GB. Runtimes 25, it keeps the base's qwen3_5_moe architecture, which llama.cpp, vLLM, SGLang and Transformers run in released versions, and Ollama 0.40.14 runs through the llama.cpp build it pins. Builds 0, no quantised build from the publisher. Terms 15, Apache 2.0 like its base. Download 10, not gated. Hosted 0, one inference provider, Featherless AI, where the line needs two. 10 + 25 + 0 + 15 + 10 + 0 = 60.

Inkling 2 Small 40

Memory 0 of 30, the smallest build is Thinking Machines' NVFP4 checkpoint at 393.5 GB, about 472 GB with a fifth added, above the 256 GB line. Runtimes 0, no released version of the six runs it; vLLM and SGLang serve it from their own images and Transformers has it on its main branch only. Builds 15, two precisions from the publisher (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 serves it as beta serverless inference, and Together is live on Hugging Face. 0 + 0 + 15 + 10 + 10 + 5 = 40.

Risk Inkling 2 Small +10

BigBang-v1 55

File safety 25, safetensors only and nothing from the repository runs. Provenance 15, the files are in the publisher's own organisation with a SHA-256 for every weight file. Safety evaluation 0. Agent guidance 0. Licence risk 15, plain Apache 2.0 that hasn't changed. Security programme 0, no website or security contact. 25 + 15 + 0 + 0 + 15 + 0 = 55.

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 runBigBang-v1Inkling 2 SmallEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%256040BigBang-v1 +20
Risk20%205565Inkling 2 Small +10
Agent interface10%106085Inkling 2 Small +25
Documentation and upkeep10%104667Inkling 2 Small +21
Negative events≤1500
TotalC 56.3/100C 58.8/100

Facts side by side

FactBigBang-v1Inkling 2 Small
KindOpen-weight modelOpen-weight model
VendorThe Endless Frontier (endless-frontier)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 release2026-08-062026-11-12
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviews2.3/5 (4)none

How the scores have moved

BigBang-v1

Inkling 2 Small

Verdicts

BigBang-v1

A Qwen3.6-35B-A3B fine-tuned on synthetic research problems, under plain Apache 2.0, for search, science and coding work. The publisher ships BF16 only, about 86 GB to run, and has no report, safety results or replies to questions, so smaller builds and support come from others.

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

BigBang-v1

  1. On the reference machine use vllm serve endless-frontier/BigBang-v1 --max-model-len 131072 --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder
  2. The card says to keep at least 128K of context so its thinking isn't cut short
  3. Thinking control isn't documented, try the base template's enable_thinking false in chat_template_kwargs and check the output
  4. For Ollama or llama.cpp you'll need someone else's GGUF; the publisher ships BF16 safetensors only
  5. Validate JSON output yourself or use the runtime's guided decoding

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, BigBang-v1 or Inkling 2 Small?

Inkling 2 Small scores 58.8 (C) on agent readiness against BigBang-v1's 56.3 (C), and leads in 3 of 4 scored categories. BigBang-v1 leads on reach.

Other comparisons with BigBang-v1 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