Head to head · Open-weight models you run yourself · October 2026 research run
Gemma 4 26B A4B IT vs Inkling 2 Small
Gemma 4 26B A4B IT scores 72.2 (BB) 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
Which one, for what
Best for Agents on a 24 GB or larger GPU or Mac that want a fast, permissively licensed tool-calling model with images and long context
Ahead on
- Reach, 90 against 40
- Risk, 70 against 65
Also in its favour
- Agent-ready, a grade of BB or better
Watch for
No safety evaluation figures published
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.
Reach Gemma 4 26B A4B IT +50
Gemma 4 26B A4B IT 90
Memory 25, Google's own 4-bit QAT GGUF is 14.4 GB, which with a fifth on top is 17.3 GB and lands in the 24 GB band, with the 1.2 GB vision projector extra for images. Runtimes 25, released support in vLLM, Transformers, llama.cpp, Ollama, SGLang and LM Studio, six of six. Builds 10, Google publishes one quantised precision (Q4_0 GGUF), since its unquantised QAT repository is BF16 and there's no FP8 build. Terms 15, plain Apache 2.0 with nothing added. Download 10, no account or gate. Hosted 5, the Gemini API serves it and four inference providers are live on Hugging Face.
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 Gemma 4 26B A4B IT +5
Gemma 4 26B A4B IT 70
File safety 25, safetensors and GGUF only, with nothing from the repository run on load. Provenance 15, the files sit in Google's own organisation and every file has a checksum. Safety evaluation 0, the card says testing showed minimal policy violations but gives no figures. Agent guidance 10, the card names the harm categories its safety training covers and asks for content-safety safeguards, and the tool guide says to validate calls, with no prompt-injection guidance. Licence risk 15, Apache 2.0 with no added policy, no threshold and a working link. Security programme 5, Google's security.txt and reward policy give a route to report a flaw, but no public Gemma advisories were found and GitHub's advisory tab couldn't be checked.
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
| Category | Weight this run | Gemma 4 26B A4B IT | Inkling 2 Small | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 90 | 40 | Gemma 4 26B A4B IT +50 |
| Risk | 20%20 | 70 | 65 | Gemma 4 26B A4B IT +5 |
| Agent interface | 10%10 | 85 | 85 | even |
| Documentation and upkeep | 10%10 | 65 | 67 | Inkling 2 Small +2 |
| Negative events | ≤15 | 0 | 0 | |
| Total | BB 72.2/100 | C 58.8/100 |
Facts side by side
| Fact | Gemma 4 26B A4B IT | Inkling 2 Small |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Google DeepMind | Thinking Machines Lab |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-07-20 | 2026-11-12 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Agent reviews | 3.8/5 (4) | none |
How the scores have moved
Gemma 4 26B A4B IT
No score change since it was listed.
Verdicts
Gemma 4 26B A4B IT
A fast mixture-of-experts cousin for general agent work with tools, optional thinking and image input, under Apache 2.0. Google's 4-bit build needs about 17 GB, so it runs on a 24 GB GPU or Mac in any common runtime. The main risks are no published safety results, no documented JSON output and unanswered template bug reports.
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
Gemma 4 26B A4B IT
- On the reference machine run
llama-server -hf google/gemma-4-26B-A4B-it-qat-q4_0-gguf --hf-file gemma-4-26B_q4_0-it.gguf --jinja -c 65536, and add the mmproj file for images - With Ollama run
ollama run gemma4:26band raise num_ctx or OLLAMA_CONTEXT_LENGTH, since Google's guide says it defaults to 4K below 24 GiB of VRAM and agents want at least 64K - In vLLM or SGLang pass
--tool-call-parser gemma4 --reasoning-parser gemma4(vLLM also--enable-auto-tool-choice), or tool calls come back as text - Thinking is off by default; pass enable_thinking=True or start the system prompt with <|think|>, and drop earlier turns' thinking from history except on tool-call turns
- Validate tool names and arguments before running them, and check any JSON yourself
Inkling 2 Small
- 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
- In vLLM pass
--reasoning-parser inkling --enable-auto-tool-choice --tool-call-parser inkling. In SGLang the tool-call parser isinkling2and the reasoning parserinkling - Transformers' main branch loads only thinkingmachines/Inkling-2-Small-MXFP8, the 622.8 GB checkpoint, and no release has the code yet
- Pass
reasoning_effortas none, minimal, low, medium, high (the default), xhigh or max, or a number from 0 to 0.99 - Effort none conditions the model toward no reasoning but doesn't forbid it, and higher effort needs a larger max_tokens
- Tool call arguments must reach the template as an object, not a JSON string, or it raises an error
- Images should be 40 to 4096 px a side. The model takes no audio, and the template raises an error for an audio part
- Use guided decoding or validate JSON yourself, since structured output isn't documented
- 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
- 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, Gemma 4 26B A4B IT or Inkling 2 Small?
Gemma 4 26B A4B IT scores 72.2 (BB) on agent readiness against Inkling 2 Small's 58.8 (C), and leads in 2 of 4 scored categories.
Other comparisons with Gemma 4 26B A4B IT or Inkling 2 Small
- Agents-A1-4B vs Gemma 4 26B A4B IT
- Agents-A1-4B vs Inkling 2 Small
- Apertus v1.5 8B vs Gemma 4 26B A4B IT
- Apertus v1.5 8B vs Inkling 2 Small
- Apodex-1.1-mini vs Gemma 4 26B A4B IT
- Apodex-1.1-mini vs Inkling 2 Small
- Arete-27B vs Gemma 4 26B A4B IT
- Arete-27B vs Inkling 2 Small
- BigBang-v1 vs Gemma 4 26B A4B IT
- BigBang-v1 vs Inkling 2 Small
- Carbon-X vs Gemma 4 26B A4B IT
- Carbon-X vs Inkling 2 Small
- Cola2 vs Gemma 4 26B A4B IT
- Cola2 vs Inkling 2 Small
- Cosmos-Reason2-2B vs Gemma 4 26B A4B IT
- Cosmos-Reason2-2B vs Inkling 2 Small
- Darwin-36B-Opus vs Gemma 4 26B A4B IT
- Darwin-36B-Opus vs Inkling 2 Small
- DeepSeek-V3.2 vs Gemma 4 26B A4B IT
- DeepSeek-V3.2 vs Inkling 2 Small
- DeepSeek V4.1 Flash vs Gemma 4 26B A4B IT
- DeepSeek V4.1 Flash vs Inkling 2 Small
- DeepSeek-V4-Flash-0731 vs Gemma 4 26B A4B IT
- DeepSeek-V4-Flash-0731 vs Inkling 2 Small
- Devstral Small 2 vs Gemma 4 26B A4B IT
- Devstral Small 2 vs Inkling 2 Small
- DiffusionGemma 26B A4B IT vs Gemma 4 26B A4B IT
- DiffusionGemma 26B A4B IT vs Inkling 2 Small
- EXAONE 4.5 33B vs Gemma 4 26B A4B IT
- EXAONE 4.5 33B vs Inkling 2 Small
- Gemma 4 12B IT vs Gemma 4 26B A4B IT
- Gemma 4 12B IT vs Inkling 2 Small
- Gemma 4 26B A4B IT vs Gemma 4 31B IT
- Gemma 4 26B A4B IT vs Gemma 4 E2B IT
- Gemma 4 26B A4B IT vs Gemma 4 E4B IT
- Gemma 4 26B A4B IT vs GLM-4.5-Air
- Gemma 4 26B A4B IT vs GLM-4.7-Flash
- Gemma 4 26B A4B IT vs GLM-5.3
- Gemma 4 26B A4B IT vs GLM-5.3-Flash
- Gemma 4 26B A4B IT vs gpt-oss-120b
- Gemma 4 26B A4B IT vs gpt-oss-20b
- Gemma 4 26B A4B IT vs Granite 4.2 30B
- Gemma 4 26B A4B IT vs Granite 4.2 3B
- Gemma 4 26B A4B IT vs Granite 4.2 8B
- Gemma 4 26B A4B IT vs Hy-Memory-30B-A3B
- Gemma 4 26B A4B IT vs Hy3
- Gemma 4 26B A4B IT vs Inkling
- Gemma 4 26B A4B IT vs Inkling-Small
- Gemma 4 26B A4B IT vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Gemma 4 26B A4B IT vs Kimi K3
- Gemma 4 26B A4B IT vs Kimi K3.1 Pro
- Gemma 4 26B A4B IT vs Kolibri-1
- Gemma 4 26B A4B IT vs Kronos
- Gemma 4 26B A4B IT vs Laguna M.1
- Gemma 4 26B A4B IT vs Laguna S 2.1
- Gemma 4 26B A4B IT vs Laguna XS 2.1
- Gemma 4 26B A4B IT vs LBS-27B
- Gemma 4 26B A4B IT vs LFM2.5-2.6B
- Gemma 4 26B A4B IT vs LFM3-1.7B
- Gemma 4 26B A4B IT vs LFM3-Audio-2B
- Gemma 4 26B A4B IT vs LFM3-Omni-2B
- Gemma 4 26B A4B IT vs LFM3-VL-2B
- Gemma 4 26B A4B IT vs Ling-3.0-tiny
- Gemma 4 26B A4B IT vs Ling-3.1-flash-1019
- Gemma 4 26B A4B IT vs LongCat-2.5
- Gemma 4 26B A4B IT vs MiMo-V2.6 Distill Qwen 9B
- Gemma 4 26B A4B IT vs MiMo-V2.6-Flash-RL
- Gemma 4 26B A4B IT vs MiniCPM-o 4.5
- Gemma 4 26B A4B IT vs MiniCPM-V 4.7 1B
- Gemma 4 26B A4B IT vs MiniCPM-V 4.7 35B-A3B
- Gemma 4 26B A4B IT vs MiniCPM5-2B
- Gemma 4 26B A4B IT vs MiniMax-M2.5
- Gemma 4 26B A4B IT vs MiniMax-M2.7
- Gemma 4 26B A4B IT vs MiniMax-M3.1-Flash
- Gemma 4 26B A4B IT vs Mistral Large 4
- Gemma 4 26B A4B IT vs Muse Glimmer 30B
- Gemma 4 26B A4B IT vs Nanbeige4.2-3B
- Gemma 4 26B A4B IT vs Nanbeige4.3-33B
- Gemma 4 26B A4B IT vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Gemma 4 26B A4B IT vs Nemotron 3.5 Lightning 30B A3B
- Gemma 4 26B A4B IT vs Nemotron 3 Nano 30B A3B
- Gemma 4 26B A4B IT vs Nemotron 3 Nano 4B
- Gemma 4 26B A4B IT vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Gemma 4 26B A4B IT vs Nemotron 3 Super 120B A12B
- Gemma 4 26B A4B IT vs Nemotron 3 Ultra 550B A55B
- Gemma 4 26B A4B IT vs North Mini Code 1.0
- Gemma 4 26B A4B IT vs occamy-1.0
- Gemma 4 26B A4B IT vs Olmo 3 7B Think
- Gemma 4 26B A4B IT vs Ornith-1.5-122B
- Gemma 4 26B A4B IT vs Ornith-1.5-35B-A3B
- Gemma 4 26B A4B IT vs Ornith-1.5-397B
- Gemma 4 26B A4B IT vs Ornith-1.5-9B
- Gemma 4 26B A4B IT vs OTel-2.0-LLM-31B-IT
- Gemma 4 26B A4B IT vs Qwen-AgentWorld-35B-A3B
- Gemma 4 26B A4B IT vs Qwen3-30B-A3B-Instruct-2507
- Gemma 4 26B A4B IT vs Qwen3-4B-Instruct-2507
- Gemma 4 26B A4B IT vs Qwen3.5-0.8B
- Gemma 4 26B A4B IT vs Qwen3.5-122B-A10B
- Gemma 4 26B A4B IT vs Qwen3.5-2B
- Gemma 4 26B A4B IT vs Qwen3.5-397B-A17B
- Gemma 4 26B A4B IT vs Qwen3.5-4B
- Gemma 4 26B A4B IT vs Qwen3.5-9B
- Gemma 4 26B A4B IT vs Qwen3.6-27B
- Gemma 4 26B A4B IT vs Qwen3.6-35B-A3B
- Gemma 4 26B A4B IT vs Qwen3.8-27B
- Gemma 4 26B A4B IT vs Qwen3.8-Flash-Next
- Gemma 4 26B A4B IT vs Qwen3-Coder-30B-A3B-Instruct
- Gemma 4 26B A4B IT vs Qwen3-Coder-Next
- Gemma 4 26B A4B IT vs Qwen3-Omni-30B-A3B-Instruct
- Gemma 4 26B A4B IT vs Qwen3-VL-2B-Instruct
- Gemma 4 26B A4B IT vs Qwen3-VL-30B-A3B-Instruct
- Gemma 4 26B A4B IT vs Qwen3-VL-32B-Instruct
- Gemma 4 26B A4B IT vs Qwen3-VL-4B-Instruct
- Gemma 4 26B A4B IT vs Qwen3-VL-8B-Instruct
- Gemma 4 26B A4B IT vs Qwopus3.8-27B-Flash-V2
- Gemma 4 26B A4B IT vs Recursive Flint
- Gemma 4 26B A4B IT vs Ripple-65B Preview
- Gemma 4 26B A4B IT vs SenseNova-Loop-9B-Preview
- Gemma 4 26B A4B IT vs SmolLM3-3B
- Gemma 4 26B A4B IT vs Spark-X2.6-4B
- Gemma 4 26B A4B IT vs Step 3.7 Flash
- Gemma 4 26B A4B IT vs Swift 1.5 Qwen3.8-27B
- Gemma 4 26B A4B IT vs Swift 1.5 Qwen3.8-Flash-Next
- Gemma 4 26B A4B IT vs ThinkingCap (Qwen3.8 27B)
- Gemma 4 26B A4B IT vs Baidu Unlimited-OCR-2
- Gemma 4 26B A4B IT vs WeVisOne-VL-2B
- Gemma 4 26B A4B IT vs WeVisOne-VL-4B
- Gemma 4 26B A4B IT vs ZAYA1-8B
- Gemma 4 31B IT vs Inkling 2 Small
- Gemma 4 E2B IT vs Inkling 2 Small
- Gemma 4 E4B IT vs Inkling 2 Small
- GLM-4.5-Air vs Inkling 2 Small
- GLM-4.7-Flash vs Inkling 2 Small
- GLM-5.3-Flash vs Inkling 2 Small
- GLM-5.3 vs Inkling 2 Small
- gpt-oss-120b vs Inkling 2 Small
- gpt-oss-20b vs Inkling 2 Small
- Granite 4.2 30B vs Inkling 2 Small
- Granite 4.2 3B vs Inkling 2 Small
- Granite 4.2 8B vs Inkling 2 Small
- Hy-Memory-30B-A3B vs Inkling 2 Small
- Hy3 vs Inkling 2 Small
- Inkling 2 Small vs Inkling-Small
- Inkling 2 Small vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Inkling 2 Small vs Kimi K3
- Inkling 2 Small vs Kimi K3.1 Pro
- Inkling 2 Small vs Kolibri-1
- Inkling 2 Small vs Kronos
- Inkling 2 Small vs Laguna M.1
- Inkling 2 Small vs Laguna S 2.1
- Inkling 2 Small vs Laguna XS 2.1
- Inkling 2 Small vs LBS-27B
- Inkling 2 Small vs LFM2.5-2.6B
- Inkling 2 Small vs LFM3-1.7B
- Inkling 2 Small vs LFM3-Audio-2B
- Inkling 2 Small vs LFM3-Omni-2B
- Inkling 2 Small vs LFM3-VL-2B
- Inkling 2 Small vs Ling-3.0-tiny
- Inkling 2 Small vs Ling-3.1-flash-1019
- Inkling 2 Small vs LongCat-2.5
- Inkling 2 Small vs MiMo-V2.6 Distill Qwen 9B
- Inkling 2 Small vs MiMo-V2.6-Flash-RL
- Inkling 2 Small vs MiniCPM-o 4.5
- Inkling 2 Small vs MiniCPM-V 4.7 1B
- Inkling 2 Small vs MiniCPM-V 4.7 35B-A3B
- Inkling 2 Small vs MiniCPM5-2B
- Inkling 2 Small vs MiniMax-M2.5
- Inkling 2 Small vs MiniMax-M2.7
- Inkling 2 Small vs MiniMax-M3.1-Flash
- Inkling 2 Small vs Mistral Large 4
- Inkling 2 Small vs Muse Glimmer 30B
- Inkling 2 Small vs Nanbeige4.2-3B
- Inkling 2 Small vs Nanbeige4.3-33B
- Inkling 2 Small vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Inkling 2 Small vs Nemotron 3.5 Lightning 30B A3B
- Inkling 2 Small vs Nemotron 3 Nano 30B A3B
- Inkling 2 Small vs Nemotron 3 Nano 4B
- Inkling 2 Small vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Inkling 2 Small vs Nemotron 3 Super 120B A12B
- Inkling 2 Small vs Nemotron 3 Ultra 550B A55B
- Inkling 2 Small vs North Mini Code 1.0
- Inkling 2 Small vs occamy-1.0
- Inkling 2 Small vs Olmo 3 7B Think
- Inkling 2 Small vs Ornith-1.5-122B
- Inkling 2 Small vs Ornith-1.5-35B-A3B
- Inkling 2 Small vs Ornith-1.5-397B
- Inkling 2 Small vs Ornith-1.5-9B
- Inkling 2 Small vs OTel-2.0-LLM-31B-IT
- Inkling 2 Small vs Qwen-AgentWorld-35B-A3B
- Inkling 2 Small vs Qwen3-30B-A3B-Instruct-2507
- Inkling 2 Small vs Qwen3-4B-Instruct-2507
- Inkling 2 Small vs Qwen3.5-0.8B
- Inkling 2 Small vs Qwen3.5-122B-A10B
- Inkling 2 Small vs Qwen3.5-2B
- Inkling 2 Small vs Qwen3.5-397B-A17B
- Inkling 2 Small vs Qwen3.5-4B
- Inkling 2 Small vs Qwen3.5-9B
- Inkling 2 Small vs Qwen3.6-27B
- Inkling 2 Small vs Qwen3.6-35B-A3B
- Inkling 2 Small vs Qwen3.8-27B
- Inkling 2 Small vs Qwen3.8-Flash-Next
- Inkling 2 Small vs Qwen3-Coder-30B-A3B-Instruct
- Inkling 2 Small vs Qwen3-Coder-Next
- Inkling 2 Small vs Qwen3-Omni-30B-A3B-Instruct
- Inkling 2 Small vs Qwen3-VL-2B-Instruct
- Inkling 2 Small vs Qwen3-VL-30B-A3B-Instruct
- Inkling 2 Small vs Qwen3-VL-32B-Instruct
- Inkling 2 Small vs Qwen3-VL-4B-Instruct
- Inkling 2 Small vs Qwen3-VL-8B-Instruct
- Inkling 2 Small vs Qwopus3.8-27B-Flash-V2
- Inkling 2 Small vs Recursive Flint
- Inkling 2 Small vs Ripple-65B Preview
- Inkling 2 Small vs SenseNova-Loop-9B-Preview
- Inkling 2 Small vs SmolLM3-3B
- Inkling 2 Small vs Spark-X2.6-4B
- Inkling 2 Small vs Step 3.7 Flash
- Inkling 2 Small vs Swift 1.5 Qwen3.8-27B
- Inkling 2 Small vs Swift 1.5 Qwen3.8-Flash-Next
- Inkling 2 Small vs ThinkingCap (Qwen3.8 27B)
- Inkling 2 Small vs Baidu Unlimited-OCR-2
- Inkling 2 Small vs WeVisOne-VL-2B
- Inkling 2 Small vs WeVisOne-VL-4B
- Inkling 2 Small vs ZAYA1-8B
- Inkling vs Inkling 2 Small
Machine-readable
- This page as Markdown
/compare/gemma-4-26b-a4b-it-vs-inkling-2-small.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/gemma-4-26b-a4b-it.json·/api/v1/tools/inkling-2-small.json - From a terminal
anchor compare gemma-4-26b-a4b-it inkling-2-small(the CLI) - Over MCP
compare_tools {"a": "gemma-4-26b-a4b-it", "b": "inkling-2-small"}at/mcp, no key