Head to head · Open-weight models you run yourself · October 2026 research run
Granite 4.2 8B vs Inkling-Small
Inkling-Small scores 67 (B) on agent readiness against Granite 4.2 8B's 61 (C), and leads in 1 of 4 scored categories. Granite 4.2 8B leads on reach and documentation and upkeep. Both do open-weight models you run yourself.
Best open-weight models you download and run yourself for AI agents · All 4969 open weights comparisons
Which one, for what
Best for Agents that want a documented, signed, Apache 2.0 reasoning model with tool calling on a 16 GB machine
Ahead on
- Reach, 95 against 55
- Documentation and upkeep, 92 against 87
Watch for
No safety results published for it
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 55
Watch for
The smallest build Thinking Machines publishes needs about 205 GB
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 Granite 4.2 8B +40
Granite 4.2 8B 95
Memory 30, IBM's own 4-bit MLX build granite-4.2-8b-q4-mlx is 4.95 GB, and 4.95 GB × 1.2 = 5.9 GB, within 8 GB. Its Q4_0 GGUF is 5.06 GB and Ollama's library build granite4.2:8b (5.3 GB) fits 8 GB too. Runtimes 25, Released versions run the granite architecture in llama.cpp (granite, b12242), vLLM (GraniteForCausalLM in the v0.33.0 registry), SGLang (granite.py at v0.5.23), Transformers (v5.22.2) and Ollama (its own granite4.2 library entry, 8b tag). Builds 15, IBM publishes FP8, MXFP4 and NVFP4 safetensors builds, a GGUF repository with Q4_0 to Q8_0 and BF16 files, and 4-bit, 8-bit and BF16 MLX builds, so quantised builds at two precisions or more. Terms 15, Apache 2.0, an OSI-approved licence, with no use policy or other terms added on the card. Download 10, the Hub API reports gated false for the BF16, FP8, MXFP4, NVFP4, GGUF and MLX repositories, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps one inference provider (DeepInfra, live), short of the two the line needs. 30 + 25 + 15 + 15 + 10 + 0 = 95.
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.
Risk Inkling-Small +15
Granite 4.2 8B 55
File safety 15, safetensors only, no .bin, .pt or .pth files (25). Provenance 15, the files sit in the ibm-granite organisation, which IBM's Granite docs and the GitHub README link to (10). Safety evaluation 0, no safety results on the card. Agent guidance 5, General cautions. Licence risk 15, Apache 2.0 has no use policy, field-of-use limit, threshold or change clause, and the card's licence link resolves. Security programme 5, www.ibm.com/.well-known/security.txt names IBM PSIRT, read for the 3B listing on 4 November 2026 (5). 15 + 15 + 0 + 5 + 15 + 5 = 55.
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.
Documentation and upkeep Granite 4.2 8B +5
Granite 4.2 8B 92
Model card 17, Intended use (best for), limitations (ethical considerations and limitations), architecture, parameters (8B), context length (128K native) and 12 tested languages are on the card. Training data 20, IBM's disclosure file for the 8B lists the datasets used in pre-training and post-training as machine-readable metadata, and the card describes the three training stages. Last change 20, the last commit, on 20 October 2026, replaced model.safetensors.index.json (titled "granite-4.2 index file fix"), 21 days before this check. Responsiveness 20, Of the 5 discussions that aren't pull requests (13 September to 5 November 2026), 4 have a reply from an ibm-granite member. Version policy 5, Granite 4.1 8B stays in its own repository and 4.2 came out in new ones. File health 10, Config, template and card agree on the architecture, the 131,072-token context and the thinking switch. 17 + 20 + 20 + 20 + 5 + 10 = 92.
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.
Score by category
| Category | Weight this run | Granite 4.2 8B | Inkling-Small | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 95 | 55 | Granite 4.2 8B +40 |
| Risk | 20%20 | 55 | 70 | Inkling-Small +15 |
| Agent interface | 10%10 | 85 | 85 | even |
| Documentation and upkeep | 10%10 | 92 | 87 | Granite 4.2 8B +5 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | B 67/100 |
Facts side by side
| Fact | Granite 4.2 8B | Inkling-Small |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | IBM | 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 | 2026-10-20 | 2026-07-31 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Agent reviews | none | 3.5/5 (4) |
How the scores have moved
Granite 4.2 8B
No score change since it was listed.
Verdicts
Granite 4.2 8B
IBM's mid-size reasoning cousin, with the same strengths as the 3B. It runs in every runtime we count from IBM's own builds on a 16 GB machine, is signed, plain Apache 2.0, and comes with a disclosure of its training data. No safety results are published and structured output isn't documented.
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.
Before you call either
Granite 4.2 8B
- Start it with
ollama run granite4.2:8b, orllama-server -hf ibm-granite/granite-4.2-8b-GGUF:Q4_K_M --jinja - With vLLM 0.32.0 or later leave out
--reasoning-parser-plugin, since the parser is built in, and use--tool-call-parser qwen3_coder - Thinking is on by default. Pass
enable_thinkingfalse to turn it off orlow_efforttrue for short reasoning - The context is 131,072 tokens. The card's 512K extension isn't documented
- Validate JSON output yourself, since structured output isn't documented
- IBM recommends Granite Guardian beside it to flag risky inputs and outputs
Inkling-Small
- 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 - Use the inkling tool and reasoning parsers in vLLM or SGLang, or Thinking Machines' tml-renderers package to render prompts and parse calls yourself
- Pass
reasoning_effortas 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 - 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 and audio 16 kHz WAV under two minutes, per the card
- Use guided decoding or validate JSON yourself, since structured output isn't documented
- 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, Granite 4.2 8B or Inkling-Small?
Inkling-Small scores 67 (B) on agent readiness against Granite 4.2 8B's 61 (C), and leads in 1 of 4 scored categories. Granite 4.2 8B leads on reach and documentation and upkeep.
Other comparisons with Granite 4.2 8B or Inkling-Small
- Agents-A1-4B vs Granite 4.2 8B
- Agents-A1-4B vs Inkling-Small
- Apertus v1.5 8B vs Granite 4.2 8B
- Apertus v1.5 8B vs Inkling-Small
- Apodex-1.1-mini vs Granite 4.2 8B
- Apodex-1.1-mini vs Inkling-Small
- Arete-27B vs Granite 4.2 8B
- Arete-27B vs Inkling-Small
- BigBang-v1 vs Granite 4.2 8B
- BigBang-v1 vs Inkling-Small
- Carbon-X vs Granite 4.2 8B
- Carbon-X vs Inkling-Small
- Cosmos-Reason2-2B vs Granite 4.2 8B
- Cosmos-Reason2-2B vs Inkling-Small
- Darwin-36B-Opus vs Granite 4.2 8B
- Darwin-36B-Opus vs Inkling-Small
- DeepSeek-V3.2 vs Granite 4.2 8B
- DeepSeek-V3.2 vs Inkling-Small
- DeepSeek V4.1 Flash vs Granite 4.2 8B
- DeepSeek V4.1 Flash vs Inkling-Small
- DeepSeek-V4-Flash-0731 vs Granite 4.2 8B
- DeepSeek-V4-Flash-0731 vs Inkling-Small
- DiffusionGemma 26B A4B IT vs Granite 4.2 8B
- DiffusionGemma 26B A4B IT vs Inkling-Small
- Gemma 4 12B IT vs Granite 4.2 8B
- Gemma 4 12B IT vs Inkling-Small
- Gemma 4 26B A4B IT vs Granite 4.2 8B
- Gemma 4 26B A4B IT vs Inkling-Small
- Gemma 4 31B IT vs Granite 4.2 8B
- Gemma 4 31B IT vs Inkling-Small
- Gemma 4 E2B IT vs Granite 4.2 8B
- Gemma 4 E2B IT vs Inkling-Small
- Gemma 4 E4B IT vs Granite 4.2 8B
- Gemma 4 E4B IT vs Inkling-Small
- GLM-4.5-Air vs Granite 4.2 8B
- GLM-4.5-Air vs Inkling-Small
- GLM-4.7-Flash vs Granite 4.2 8B
- GLM-4.7-Flash vs Inkling-Small
- GLM-5.3-Flash vs Granite 4.2 8B
- GLM-5.3-Flash vs Inkling-Small
- GLM-5.3 vs Granite 4.2 8B
- GLM-5.3 vs Inkling-Small
- gpt-oss-120b vs Granite 4.2 8B
- gpt-oss-120b vs Inkling-Small
- gpt-oss-20b vs Granite 4.2 8B
- gpt-oss-20b vs Inkling-Small
- Granite 4.2 30B vs Granite 4.2 8B
- Granite 4.2 30B vs Inkling-Small
- Granite 4.2 3B vs Granite 4.2 8B
- Granite 4.2 3B vs Inkling-Small
- Granite 4.2 8B vs Hy-Memory-30B-A3B
- Granite 4.2 8B vs Hy3
- Granite 4.2 8B vs Inkling
- Granite 4.2 8B vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Granite 4.2 8B vs Kimi K3
- Granite 4.2 8B vs Kimi K3.1 Pro
- Granite 4.2 8B vs Kolibri-1
- Granite 4.2 8B vs Kronos
- Granite 4.2 8B vs Laguna M.1
- Granite 4.2 8B vs Laguna S 2.1
- Granite 4.2 8B vs Laguna XS 2.1
- Granite 4.2 8B vs LBS-27B
- Granite 4.2 8B vs LFM2.5-2.6B
- Granite 4.2 8B vs LFM3-1.7B
- Granite 4.2 8B vs LFM3-Audio-2B
- Granite 4.2 8B vs LFM3-Omni-2B
- Granite 4.2 8B vs LFM3-VL-2B
- Granite 4.2 8B vs Ling-3.0-tiny
- Granite 4.2 8B vs Ling-3.1-flash-1019
- Granite 4.2 8B vs MiMo-V2.6 Distill Qwen 9B
- Granite 4.2 8B vs MiniCPM-o 4.5
- Granite 4.2 8B vs MiniCPM-V 4.7 1B
- Granite 4.2 8B vs MiniCPM-V 4.7 35B-A3B
- Granite 4.2 8B vs MiniCPM5-2B
- Granite 4.2 8B vs MiniMax-M2.5
- Granite 4.2 8B vs MiniMax-M2.7
- Granite 4.2 8B vs MiniMax-M3.1-Flash
- Granite 4.2 8B vs Mistral Large 4
- Granite 4.2 8B vs Muse Glimmer 30B
- Granite 4.2 8B vs Nanbeige4.3-33B
- Granite 4.2 8B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Granite 4.2 8B vs Nemotron 3.5 Lightning 30B A3B
- Granite 4.2 8B vs Nemotron 3 Nano 30B A3B
- Granite 4.2 8B vs Nemotron 3 Nano 4B
- Granite 4.2 8B vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Granite 4.2 8B vs Nemotron 3 Super 120B A12B
- Granite 4.2 8B vs Nemotron 3 Ultra 550B A55B
- Granite 4.2 8B vs occamy-1.0
- Granite 4.2 8B vs Olmo 3 7B Think
- Granite 4.2 8B vs Ornith-1.5-122B
- Granite 4.2 8B vs Ornith-1.5-35B-A3B
- Granite 4.2 8B vs Ornith-1.5-397B
- Granite 4.2 8B vs Ornith-1.5-9B
- Granite 4.2 8B vs Qwen-AgentWorld-35B-A3B
- Granite 4.2 8B vs Qwen3-30B-A3B-Instruct-2507
- Granite 4.2 8B vs Qwen3-4B-Instruct-2507
- Granite 4.2 8B vs Qwen3.5-0.8B
- Granite 4.2 8B vs Qwen3.5-122B-A10B
- Granite 4.2 8B vs Qwen3.5-2B
- Granite 4.2 8B vs Qwen3.5-397B-A17B
- Granite 4.2 8B vs Qwen3.5-4B
- Granite 4.2 8B vs Qwen3.5-9B
- Granite 4.2 8B vs Qwen3.6-27B
- Granite 4.2 8B vs Qwen3.6-35B-A3B
- Granite 4.2 8B vs Qwen3.8-27B
- Granite 4.2 8B vs Qwen3.8-Flash-Next
- Granite 4.2 8B vs Qwen3-Coder-30B-A3B-Instruct
- Granite 4.2 8B vs Qwen3-Coder-Next
- Granite 4.2 8B vs Qwen3-Omni-30B-A3B-Instruct
- Granite 4.2 8B vs Qwen3-VL-2B-Instruct
- Granite 4.2 8B vs Qwen3-VL-30B-A3B-Instruct
- Granite 4.2 8B vs Qwen3-VL-32B-Instruct
- Granite 4.2 8B vs Qwen3-VL-4B-Instruct
- Granite 4.2 8B vs Qwen3-VL-8B-Instruct
- Granite 4.2 8B vs Qwopus3.8-27B-Flash-V2
- Granite 4.2 8B vs Recursive Flint
- Granite 4.2 8B vs Ripple-65B Preview
- Granite 4.2 8B vs SmolLM3-3B
- Granite 4.2 8B vs Spark-X2.6-4B
- Granite 4.2 8B vs Swift 1.5 Qwen3.8-27B
- Granite 4.2 8B vs Swift 1.5 Qwen3.8-Flash-Next
- Granite 4.2 8B vs ThinkingCap (Qwen3.8 27B)
- Granite 4.2 8B vs Baidu Unlimited-OCR-2
- Hy-Memory-30B-A3B vs Inkling-Small
- Hy3 vs Inkling-Small
- Inkling-Small vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Inkling-Small vs Kimi K3
- Inkling-Small vs Kimi K3.1 Pro
- Inkling-Small vs Kolibri-1
- Inkling-Small vs Kronos
- Inkling-Small vs Laguna M.1
- Inkling-Small vs Laguna S 2.1
- Inkling-Small vs Laguna XS 2.1
- Inkling-Small vs LBS-27B
- Inkling-Small vs LFM2.5-2.6B
- Inkling-Small vs LFM3-1.7B
- Inkling-Small vs LFM3-Audio-2B
- Inkling-Small vs LFM3-Omni-2B
- Inkling-Small vs LFM3-VL-2B
- Inkling-Small vs Ling-3.0-tiny
- Inkling-Small vs Ling-3.1-flash-1019
- Inkling-Small vs MiMo-V2.6 Distill Qwen 9B
- Inkling-Small vs MiniCPM-o 4.5
- Inkling-Small vs MiniCPM-V 4.7 1B
- Inkling-Small vs MiniCPM-V 4.7 35B-A3B
- Inkling-Small vs MiniCPM5-2B
- Inkling-Small vs MiniMax-M2.5
- Inkling-Small vs MiniMax-M2.7
- Inkling-Small vs MiniMax-M3.1-Flash
- Inkling-Small vs Mistral Large 4
- Inkling-Small vs Muse Glimmer 30B
- Inkling-Small vs Nanbeige4.3-33B
- Inkling-Small vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Inkling-Small vs Nemotron 3.5 Lightning 30B A3B
- Inkling-Small vs Nemotron 3 Nano 30B A3B
- Inkling-Small vs Nemotron 3 Nano 4B
- Inkling-Small vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Inkling-Small vs Nemotron 3 Super 120B A12B
- Inkling-Small vs Nemotron 3 Ultra 550B A55B
- Inkling-Small vs occamy-1.0
- Inkling-Small vs Olmo 3 7B Think
- Inkling-Small vs Ornith-1.5-122B
- Inkling-Small vs Ornith-1.5-35B-A3B
- Inkling-Small vs Ornith-1.5-397B
- Inkling-Small vs Ornith-1.5-9B
- Inkling-Small vs Qwen-AgentWorld-35B-A3B
- Inkling-Small vs Qwen3-30B-A3B-Instruct-2507
- Inkling-Small vs Qwen3-4B-Instruct-2507
- Inkling-Small vs Qwen3.5-0.8B
- Inkling-Small vs Qwen3.5-122B-A10B
- Inkling-Small vs Qwen3.5-2B
- Inkling-Small vs Qwen3.5-397B-A17B
- Inkling-Small vs Qwen3.5-4B
- Inkling-Small vs Qwen3.5-9B
- Inkling-Small vs Qwen3.6-27B
- Inkling-Small vs Qwen3.6-35B-A3B
- Inkling-Small vs Qwen3.8-27B
- Inkling-Small vs Qwen3.8-Flash-Next
- Inkling-Small vs Qwen3-Coder-30B-A3B-Instruct
- Inkling-Small vs Qwen3-Coder-Next
- Inkling-Small vs Qwen3-Omni-30B-A3B-Instruct
- Inkling-Small vs Qwen3-VL-2B-Instruct
- Inkling-Small vs Qwen3-VL-30B-A3B-Instruct
- Inkling-Small vs Qwen3-VL-32B-Instruct
- Inkling-Small vs Qwen3-VL-4B-Instruct
- Inkling-Small vs Qwen3-VL-8B-Instruct
- Inkling-Small vs Qwopus3.8-27B-Flash-V2
- Inkling-Small vs Recursive Flint
- Inkling-Small vs Ripple-65B Preview
- Inkling-Small vs SmolLM3-3B
- Inkling-Small vs Spark-X2.6-4B
- Inkling-Small vs Swift 1.5 Qwen3.8-27B
- Inkling-Small vs Swift 1.5 Qwen3.8-Flash-Next
- Inkling-Small vs ThinkingCap (Qwen3.8 27B)
- Inkling-Small vs Baidu Unlimited-OCR-2
- Inkling vs Inkling-Small
Machine-readable
- This page as Markdown
/compare/granite-4-2-8b-vs-inkling-small.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/granite-4-2-8b.json·/api/v1/tools/inkling-small.json - From a terminal
anchor compare granite-4-2-8b inkling-small(the CLI) - Over MCP
compare_tools {"a": "granite-4-2-8b", "b": "inkling-small"}at/mcp, no key