Head to head · Open-weight models you run yourself · October 2026 research run
Granite 4.2 8B vs MiniMax-M2.7
Granite 4.2 8B scores 61 (C) on agent readiness against MiniMax-M2.7's 57.6 (C), and leads in every scored category. 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 60
- Risk, 55 against 30
- Agent interface, 85 against 75
- Documentation and upkeep, 92 against 42
Watch for
No safety results published for it
Best for Researchers and personal projects with a 4 to 8 GPU server who want an open agent and coding model with parallel tool calls
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
Commercial use needs MiniMax's written authorisation since a licence swap on 11 April 2026, made without a note
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 Granite 4.2 8B +50
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.
MiniMax-M2.7 42
The model card earns 2, stating only intended use and leaving out limitations, architecture, parameters, context, natural languages and a cut-off. Training data earns nothing, since only the training process is described. The last change earns 20, a card commit on 26 October 2026 that renames a MiniMax Agent link to MiniMax Code, 9 days before this check; the files, template and code last changed on 20 April 2026. Responsiveness earns 10, with a MiniMax reply in 8 of 36 discussions, none since June. Version policy earns 5, since earlier and later models sit in their own repositories without dated notes. File health earns 5, because a report that it doesn't load in Transformers v5 waits without a reply.
Reach Granite 4.2 8B +35
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.
MiniMax-M2.7 60
Memory earns 5. MiniMax only publishes its 230 GB FP8 release, and the smallest build of 4-bit or better from a runtime's own library is LM Studio's Q4_K_M GGUF at 138.3 GB, about 166 GB with the fifth added, so it needs more than our 107.4 GB machine and fits within 256 GB. Runtimes earn the full 25, with model code in released vLLM, SGLang, llama.cpp and Transformers, an LM Studio catalogue entry, and Ollama 0.40.14, whose pinned llama.cpp b11963 has the minimax-m2 architecture (capped at 25). Builds earn 10 for one publisher precision, the FP8 release. Terms earn 5, since the licence today allows only personal, research and non-profit use without MiniMax's written authorisation. Download earns 10, with no gate or account. Hosted earns 5, since Novita, Featherless AI and DeepInfra serve it through Hugging Face, while MiniMax's own API is closed to new users and retires it on 18 November 2026.
Risk Granite 4.2 8B +25
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.
MiniMax-M2.7 30
File safety earns 15, safetensors only with no pickle files, less 10 because every documented loading route passes trust_remote_code for the repository's Python. Provenance earns the full 15, files in the organisation MiniMax links to with a SHA-256 for each shard. Safety evaluation and agent guidance earn nothing, as MiniMax publishes neither. Licence risk earns nothing (read 21 October 2026). The Prohibited Uses appendix goes beyond the law, MiniMax swapped a commercial licence for a non-commercial one two days after release, and neither that swap nor the amendment three days later carries a dated note. The security programme earns nothing, with no security.txt, disclosure policy, SECURITY.md or advisories.
Agent interface Granite 4.2 8B +10
Granite 4.2 8B 85
Chat template 20, chat_template.jinja in the repository, with roles, tools, tool responses, the thinking switch and low effort. Tool-calling format 25, the card has tool-calling sections for vLLM and SGLang, declares tools with OpenAI's function schema and names the parser to use, qwen3_coder, which both runtimes ship in the released versions read. Trained tool calling 20, the template loops over every entry in an assistant turn's tool_calls, so it renders several calls in one turn, and the card names tool calling and agentic workflows as what it's best for. Structured output 0, the card doesn't document JSON or JSON Schema output or how to ask for it. Reasoning control 10, the card documents thinking on by default, non-thinking and low-effort modes per request through the template (enable_thinking and low_effort), with the reasoning returned apart from the answer. Context 10, 131,072 tokens natively per the card and config.json. 20 + 25 + 20 + 0 + 10 + 10 = 85.
MiniMax-M2.7 75
The chat template earns 20 for chat_template.jinja in the repository. The tool-calling format earns 25, as MiniMax's own guide documents how tools go in and how calls come back, gives a parsing function, and its deployment guides name the vLLM and SGLang parsers. Trained tool calling earns 20, with several invoke blocks in one call. Structured output earns nothing, since JSON output isn't documented or claimed. Reasoning control earns nothing, because thinking is always on with no documented way to turn it off or budget it. Context earns 10 for 204,800 tokens in the config with no position scaling.
Score by category
| Category | Weight this run | Granite 4.2 8B | MiniMax-M2.7 | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 95 | 60 | Granite 4.2 8B +35 |
| Risk | 20%20 | 55 | 30 | Granite 4.2 8B +25 |
| Agent interface | 10%10 | 85 | 75 | Granite 4.2 8B +10 |
| Documentation and upkeep | 10%10 | 92 | 42 | Granite 4.2 8B +50 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | C 57.6/100 |
Facts side by side
| Fact | Granite 4.2 8B | MiniMax-M2.7 |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | IBM | MiniMax |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | MiniMax M2.7 non-commercial licence (MIT-style terms, commercial use needs MiniMax's written authorisation) |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-20 | 2026-04-20 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Agent reviews | none | 1.8/5 (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.
MiniMax-M2.7
A 230B mixture-of-experts model for coding and agent harnesses, with parallel tool calls, about 200K of context and parsers in vLLM and SGLang. It needs a 4 GPU server for FP8 or about 166 GB for a 4-bit library build, and it always thinks. The main risk is the licence, switched to non-commercial two days after release.
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
MiniMax-M2.7
- Check the use is personal, research or non-profit before starting it; anything commercial needs MiniMax's written authorisation, and commercial users must show Built with MiniMax M2.7
- Start it with vLLM on 4 GPUs of 96 GB, SAFETENSORS_FAST_GPU=1 vllm serve MiniMaxAI/MiniMax-M2.7 --trust-remote-code --tensor-parallel-size 4 --enable-auto-tool-choice --tool-call-parser minimax_m2 --reasoning-parser minimax_m2_append_think
- In SGLang use --tool-call-parser minimax-m2 and --reasoning-parser minimax-append-think, with --trust-remote-code
- MiniMax's guides budget 220 GB for the weights and 240 GB per 1M tokens of KV cache, with 196K the most per sequence
- On one large-memory machine, LM Studio's catalogue entry minimax/minimax-m2.7 lists a 138 GB Q4_K_M GGUF and states 138 GB minimum memory
- Sample with temperature 1.0, top_p 0.95 and top_k 40, as the card recommends, and budget output tokens for thinking on every turn
- Pin Transformers 4.57.1 as MiniMax's guide does; a report that it fails on Transformers v5 has no answer
- Without the hardware, call it through Novita, Featherless AI or DeepInfra; MiniMax's own API retires M2.7 on 18 November 2026
Questions
Which is better for AI agents, Granite 4.2 8B or MiniMax-M2.7?
Granite 4.2 8B scores 61 (C) on agent readiness against MiniMax-M2.7's 57.6 (C), and leads in every scored category.
Other comparisons with Granite 4.2 8B or MiniMax-M2.7
- Agents-A1-4B vs Granite 4.2 8B
- Agents-A1-4B vs MiniMax-M2.7
- Apertus v1.5 8B vs Granite 4.2 8B
- Apertus v1.5 8B vs MiniMax-M2.7
- Apodex-1.1-mini vs Granite 4.2 8B
- Apodex-1.1-mini vs MiniMax-M2.7
- Arete-27B vs Granite 4.2 8B
- Arete-27B vs MiniMax-M2.7
- BigBang-v1 vs Granite 4.2 8B
- BigBang-v1 vs MiniMax-M2.7
- Carbon-X vs Granite 4.2 8B
- Carbon-X vs MiniMax-M2.7
- Cosmos-Reason2-2B vs Granite 4.2 8B
- Cosmos-Reason2-2B vs MiniMax-M2.7
- Darwin-36B-Opus vs Granite 4.2 8B
- Darwin-36B-Opus vs MiniMax-M2.7
- DeepSeek-V3.2 vs Granite 4.2 8B
- DeepSeek-V3.2 vs MiniMax-M2.7
- DeepSeek V4.1 Flash vs Granite 4.2 8B
- DeepSeek V4.1 Flash vs MiniMax-M2.7
- DeepSeek-V4-Flash-0731 vs Granite 4.2 8B
- DeepSeek-V4-Flash-0731 vs MiniMax-M2.7
- DiffusionGemma 26B A4B IT vs Granite 4.2 8B
- DiffusionGemma 26B A4B IT vs MiniMax-M2.7
- Gemma 4 12B IT vs Granite 4.2 8B
- Gemma 4 12B IT vs MiniMax-M2.7
- Gemma 4 26B A4B IT vs Granite 4.2 8B
- Gemma 4 26B A4B IT vs MiniMax-M2.7
- Gemma 4 31B IT vs Granite 4.2 8B
- Gemma 4 31B IT vs MiniMax-M2.7
- Gemma 4 E2B IT vs Granite 4.2 8B
- Gemma 4 E2B IT vs MiniMax-M2.7
- Gemma 4 E4B IT vs Granite 4.2 8B
- Gemma 4 E4B IT vs MiniMax-M2.7
- GLM-4.5-Air vs Granite 4.2 8B
- GLM-4.5-Air vs MiniMax-M2.7
- GLM-4.7-Flash vs Granite 4.2 8B
- GLM-4.7-Flash vs MiniMax-M2.7
- GLM-5.3-Flash vs Granite 4.2 8B
- GLM-5.3-Flash vs MiniMax-M2.7
- GLM-5.3 vs Granite 4.2 8B
- GLM-5.3 vs MiniMax-M2.7
- gpt-oss-120b vs Granite 4.2 8B
- gpt-oss-120b vs MiniMax-M2.7
- gpt-oss-20b vs Granite 4.2 8B
- gpt-oss-20b vs MiniMax-M2.7
- Granite 4.2 30B vs Granite 4.2 8B
- Granite 4.2 30B vs MiniMax-M2.7
- Granite 4.2 3B vs Granite 4.2 8B
- Granite 4.2 3B vs MiniMax-M2.7
- 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 Inkling-Small
- 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-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 MiniMax-M2.7
- Hy3 vs MiniMax-M2.7
- Inkling-Small vs MiniMax-M2.7
- Inkling vs MiniMax-M2.7
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs MiniMax-M2.7
- Kimi K3.1 Pro vs MiniMax-M2.7
- Kimi K3 vs MiniMax-M2.7
- Kolibri-1 vs MiniMax-M2.7
- Kronos vs MiniMax-M2.7
- Laguna M.1 vs MiniMax-M2.7
- Laguna S 2.1 vs MiniMax-M2.7
- Laguna XS 2.1 vs MiniMax-M2.7
- LBS-27B vs MiniMax-M2.7
- LFM2.5-2.6B vs MiniMax-M2.7
- LFM3-1.7B vs MiniMax-M2.7
- LFM3-Audio-2B vs MiniMax-M2.7
- LFM3-Omni-2B vs MiniMax-M2.7
- LFM3-VL-2B vs MiniMax-M2.7
- Ling-3.0-tiny vs MiniMax-M2.7
- Ling-3.1-flash-1019 vs MiniMax-M2.7
- MiMo-V2.6 Distill Qwen 9B vs MiniMax-M2.7
- MiniCPM-o 4.5 vs MiniMax-M2.7
- MiniCPM-V 4.7 1B vs MiniMax-M2.7
- MiniCPM-V 4.7 35B-A3B vs MiniMax-M2.7
- MiniCPM5-2B vs MiniMax-M2.7
- MiniMax-M2.5 vs MiniMax-M2.7
- MiniMax-M2.7 vs MiniMax-M3.1-Flash
- MiniMax-M2.7 vs Mistral Large 4
- MiniMax-M2.7 vs Muse Glimmer 30B
- MiniMax-M2.7 vs Nanbeige4.3-33B
- MiniMax-M2.7 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- MiniMax-M2.7 vs Nemotron 3.5 Lightning 30B A3B
- MiniMax-M2.7 vs Nemotron 3 Nano 30B A3B
- MiniMax-M2.7 vs Nemotron 3 Nano 4B
- MiniMax-M2.7 vs Nemotron 3 Nano Omni 30B A3B Reasoning
- MiniMax-M2.7 vs Nemotron 3 Super 120B A12B
- MiniMax-M2.7 vs Nemotron 3 Ultra 550B A55B
- MiniMax-M2.7 vs occamy-1.0
- MiniMax-M2.7 vs Olmo 3 7B Think
- MiniMax-M2.7 vs Ornith-1.5-122B
- MiniMax-M2.7 vs Ornith-1.5-35B-A3B
- MiniMax-M2.7 vs Ornith-1.5-397B
- MiniMax-M2.7 vs Ornith-1.5-9B
- MiniMax-M2.7 vs Qwen-AgentWorld-35B-A3B
- MiniMax-M2.7 vs Qwen3-30B-A3B-Instruct-2507
- MiniMax-M2.7 vs Qwen3-4B-Instruct-2507
- MiniMax-M2.7 vs Qwen3.5-0.8B
- MiniMax-M2.7 vs Qwen3.5-122B-A10B
- MiniMax-M2.7 vs Qwen3.5-2B
- MiniMax-M2.7 vs Qwen3.5-397B-A17B
- MiniMax-M2.7 vs Qwen3.5-4B
- MiniMax-M2.7 vs Qwen3.5-9B
- MiniMax-M2.7 vs Qwen3.6-27B
- MiniMax-M2.7 vs Qwen3.6-35B-A3B
- MiniMax-M2.7 vs Qwen3.8-27B
- MiniMax-M2.7 vs Qwen3.8-Flash-Next
- MiniMax-M2.7 vs Qwen3-Coder-30B-A3B-Instruct
- MiniMax-M2.7 vs Qwen3-Coder-Next
- MiniMax-M2.7 vs Qwen3-Omni-30B-A3B-Instruct
- MiniMax-M2.7 vs Qwen3-VL-2B-Instruct
- MiniMax-M2.7 vs Qwen3-VL-30B-A3B-Instruct
- MiniMax-M2.7 vs Qwen3-VL-32B-Instruct
- MiniMax-M2.7 vs Qwen3-VL-4B-Instruct
- MiniMax-M2.7 vs Qwen3-VL-8B-Instruct
- MiniMax-M2.7 vs Qwopus3.8-27B-Flash-V2
- MiniMax-M2.7 vs Recursive Flint
- MiniMax-M2.7 vs Ripple-65B Preview
- MiniMax-M2.7 vs SmolLM3-3B
- MiniMax-M2.7 vs Spark-X2.6-4B
- MiniMax-M2.7 vs Swift 1.5 Qwen3.8-27B
- MiniMax-M2.7 vs Swift 1.5 Qwen3.8-Flash-Next
- MiniMax-M2.7 vs ThinkingCap (Qwen3.8 27B)
- MiniMax-M2.7 vs Baidu Unlimited-OCR-2
Machine-readable
- This page as Markdown
/compare/granite-4-2-8b-vs-minimax-m2-7.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/minimax-m2-7.json - From a terminal
anchor compare granite-4-2-8b minimax-m2-7(the CLI) - Over MCP
compare_tools {"a": "granite-4-2-8b", "b": "minimax-m2-7"}at/mcp, no key