Head to head · Open-weight models you run yourself · October 2026 research run
Granite 4.2 8B vs Muse Glimmer 30B
Muse Glimmer 30B scores 70 (BB) 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, agent interface 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 90
- Agent interface, 85 against 75
- Documentation and upkeep, 92 against 65
Watch for
No safety results published for it
Best for Local agents and coding with image input on one 24 to 32 GB GPU or an Apple silicon laptop, where one tool call per turn is enough
Ahead on
- Risk, 80 against 55
Also in its favour
- Agent-ready, a grade of BB or better
Watch for
One tool call per turn and no parallel calls
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 +27
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.
Muse Glimmer 30B 65
Model card 20, all seven parts present, languages as a count of more than 100. Training data 10, a general description with a 4 January 2026 cut-off and no sources or sizes. Last change 20, a card update on 20 October citing the technical report, read as a change to the files as card edits were for other listings; Meta added its own MMI evaluation results file on 22 October. Responsiveness 5, a Meta member replied to 1 of the 40 most recent non-PR discussions (re-counted on 1 November). Version policy 5, a first release. File health 5, the files agree but a chat template bug report from 11 August still has no reply.
Risk Muse Glimmer 30B +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.
Muse Glimmer 30B 80
File safety 25, safetensors and GGUF, with the ExecuTorch pos_embed.bin files read as raw embedding tables by their exact size and the Hub's scans, and no repository code runs. Provenance 15, the verified meta-models organisation Meta links, with a checksum on every file. Safety evaluation 10, Meta's own published results with stated set-ups but nothing to rerun and no outside assessor. Agent guidance 15, trained against indirect prompt injection with a principal hierarchy, and results published. Licence risk 10, 5 off for the use policy, and the policy's pointer to a latest copy leads back to the same repository file with no change clause. Security programme 5, a whitehat route in the usage policy, with no security.txt and public advisories unchecked, so scored as absent.
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.
Muse Glimmer 30B 75
Chat template 20, a Jinja file in the repository. Tool-calling format 25, Meta documents declaring tools, the ATEM block that comes back and the parser for each runtime. Trained tool calling 10, one call per turn and no parallel calls. Structured output 0, nothing documented for JSON or JSON Schema. Reasoning control 10, reasoning can't be turned off but is budgeted per request with four strength levels and returned as reasoning_content. Context 10, 131,072 tokens trained in.
Reach Granite 4.2 8B +5
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.
Muse Glimmer 30B 90
Memory 25, Meta's 16.8 GB Q4_K_M GGUF needs about 20 GB with the runtime's fifth, so it fits a 24 GB card but not 16 GB. Runtimes 25, released model code in vLLM, SGLang, Transformers, llama.cpp and Ollama's library fills the cap. Builds 15, Meta publishes GGUF and ExecuTorch 4-bit builds, read as two kinds as gemma-4-31b-it was, though all are 4-bit k-quants. Terms 10, Apache 2.0 with a usage policy that adds limits beyond the law, so a free commercial licence under a use policy. Download 10, no repository is gated. Hosted 5, Meta's API doesn't serve it but Together, Featherless AI and DeepInfra are live on its Hub page.
Score by category
| Category | Weight this run | Granite 4.2 8B | Muse Glimmer 30B | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 95 | 90 | Granite 4.2 8B +5 |
| Risk | 20%20 | 55 | 80 | Muse Glimmer 30B +25 |
| Agent interface | 10%10 | 85 | 75 | Granite 4.2 8B +10 |
| Documentation and upkeep | 10%10 | 92 | 65 | Granite 4.2 8B +27 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | BB 70/100 |
Facts side by side
| Fact | Granite 4.2 8B | Muse Glimmer 30B |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | IBM | Meta |
| 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 | yes |
| Last release | 2026-10-20 | 2026-10-20 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Agent reviews | none | 3.8/5 (4) |
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.
Muse Glimmer 30B
A dense 30B multimodal cousin for local agent and coding work with images, documented tool calls and adjustable reasoning. Meta's 17 GB GGUF fits a 24 GB card and runs in llama.cpp, Ollama, vLLM, SGLang and Transformers. The main risks are one tool call per turn, no documented JSON output and a usage policy that adds limits to Apache 2.0.
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
Muse Glimmer 30B
- Start it with
llama serve -hf meta-models/Muse-Glimmer-30B-GGUF --hf-file Muse-Glimmer-30B-KQuant-17GB-Q4_K_M.gguf -ngl 99 -c 131072 --host 127.0.0.1 --port 8080 --chat-template-kwargs '{"reasoning_strength":"high"}'on llama.cpp b10353 or later, orollama run muse-glimmeron Ollama 0.32.7 or later - In vLLM pass
--tool-call-parser muse_glimmer --reasoning-parser muse_glimmer, in SGLangmusefor both, in ExecuTorch--tool-parser atem. Without them tool calls come back as plain text - Set reasoning per request with
chat_template_kwargs.reasoning_strength(low, medium, high or xhigh). llama.cpp and ExecuTorch don't readreasoning_effort, and ExecuTorch rejects it with a 400 - Expect one tool call per turn and return each result before the next. ExecuTorch's server rejects
tool_choice="required" - Keep temperature 1.0, top_p 0.95 and top_k 64, don't run greedy, and never stop on
<|eom|> - Leave max_tokens room for reasoning, since in llama.cpp a request cut off mid-thought returns empty content with finish_reason length
- For images add Meta's 1.4 GB mmproj GGUF, which takes the build to about 22 GB with the runtime's fifth
Questions
Which is better for AI agents, Granite 4.2 8B or Muse Glimmer 30B?
Muse Glimmer 30B scores 70 (BB) 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, agent interface and documentation and upkeep.
Other comparisons with Granite 4.2 8B or Muse Glimmer 30B
- Agents-A1-4B vs Granite 4.2 8B
- Agents-A1-4B vs Muse Glimmer 30B
- Apertus v1.5 8B vs Granite 4.2 8B
- Apertus v1.5 8B vs Muse Glimmer 30B
- Apodex-1.1-mini vs Granite 4.2 8B
- Apodex-1.1-mini vs Muse Glimmer 30B
- Arete-27B vs Granite 4.2 8B
- Arete-27B vs Muse Glimmer 30B
- BigBang-v1 vs Granite 4.2 8B
- BigBang-v1 vs Muse Glimmer 30B
- Carbon-X vs Granite 4.2 8B
- Carbon-X vs Muse Glimmer 30B
- Cosmos-Reason2-2B vs Granite 4.2 8B
- Cosmos-Reason2-2B vs Muse Glimmer 30B
- Darwin-36B-Opus vs Granite 4.2 8B
- Darwin-36B-Opus vs Muse Glimmer 30B
- DeepSeek-V3.2 vs Granite 4.2 8B
- DeepSeek-V3.2 vs Muse Glimmer 30B
- DeepSeek V4.1 Flash vs Granite 4.2 8B
- DeepSeek V4.1 Flash vs Muse Glimmer 30B
- DeepSeek-V4-Flash-0731 vs Granite 4.2 8B
- DeepSeek-V4-Flash-0731 vs Muse Glimmer 30B
- DiffusionGemma 26B A4B IT vs Granite 4.2 8B
- DiffusionGemma 26B A4B IT vs Muse Glimmer 30B
- Gemma 4 12B IT vs Granite 4.2 8B
- Gemma 4 12B IT vs Muse Glimmer 30B
- Gemma 4 26B A4B IT vs Granite 4.2 8B
- Gemma 4 26B A4B IT vs Muse Glimmer 30B
- Gemma 4 31B IT vs Granite 4.2 8B
- Gemma 4 31B IT vs Muse Glimmer 30B
- Gemma 4 E2B IT vs Granite 4.2 8B
- Gemma 4 E2B IT vs Muse Glimmer 30B
- Gemma 4 E4B IT vs Granite 4.2 8B
- Gemma 4 E4B IT vs Muse Glimmer 30B
- GLM-4.5-Air vs Granite 4.2 8B
- GLM-4.5-Air vs Muse Glimmer 30B
- GLM-4.7-Flash vs Granite 4.2 8B
- GLM-4.7-Flash vs Muse Glimmer 30B
- GLM-5.3-Flash vs Granite 4.2 8B
- GLM-5.3-Flash vs Muse Glimmer 30B
- GLM-5.3 vs Granite 4.2 8B
- GLM-5.3 vs Muse Glimmer 30B
- gpt-oss-120b vs Granite 4.2 8B
- gpt-oss-120b vs Muse Glimmer 30B
- gpt-oss-20b vs Granite 4.2 8B
- gpt-oss-20b vs Muse Glimmer 30B
- Granite 4.2 30B vs Granite 4.2 8B
- Granite 4.2 30B vs Muse Glimmer 30B
- Granite 4.2 3B vs Granite 4.2 8B
- Granite 4.2 3B vs Muse Glimmer 30B
- 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-M2.7
- Granite 4.2 8B vs MiniMax-M3.1-Flash
- Granite 4.2 8B vs Mistral Large 4
- 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 Muse Glimmer 30B
- Hy3 vs Muse Glimmer 30B
- Inkling-Small vs Muse Glimmer 30B
- Inkling vs Muse Glimmer 30B
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs Muse Glimmer 30B
- Kimi K3.1 Pro vs Muse Glimmer 30B
- Kimi K3 vs Muse Glimmer 30B
- Kolibri-1 vs Muse Glimmer 30B
- Kronos vs Muse Glimmer 30B
- Laguna M.1 vs Muse Glimmer 30B
- Laguna S 2.1 vs Muse Glimmer 30B
- Laguna XS 2.1 vs Muse Glimmer 30B
- LBS-27B vs Muse Glimmer 30B
- LFM2.5-2.6B vs Muse Glimmer 30B
- LFM3-1.7B vs Muse Glimmer 30B
- LFM3-Audio-2B vs Muse Glimmer 30B
- LFM3-Omni-2B vs Muse Glimmer 30B
- LFM3-VL-2B vs Muse Glimmer 30B
- Ling-3.0-tiny vs Muse Glimmer 30B
- Ling-3.1-flash-1019 vs Muse Glimmer 30B
- MiMo-V2.6 Distill Qwen 9B vs Muse Glimmer 30B
- MiniCPM-o 4.5 vs Muse Glimmer 30B
- MiniCPM-V 4.7 1B vs Muse Glimmer 30B
- MiniCPM-V 4.7 35B-A3B vs Muse Glimmer 30B
- MiniCPM5-2B vs Muse Glimmer 30B
- MiniMax-M2.5 vs Muse Glimmer 30B
- MiniMax-M2.7 vs Muse Glimmer 30B
- MiniMax-M3.1-Flash vs Muse Glimmer 30B
- Mistral Large 4 vs Muse Glimmer 30B
- Muse Glimmer 30B vs Nanbeige4.3-33B
- Muse Glimmer 30B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Muse Glimmer 30B vs Nemotron 3.5 Lightning 30B A3B
- Muse Glimmer 30B vs Nemotron 3 Nano 30B A3B
- Muse Glimmer 30B vs Nemotron 3 Nano 4B
- Muse Glimmer 30B vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Muse Glimmer 30B vs Nemotron 3 Super 120B A12B
- Muse Glimmer 30B vs Nemotron 3 Ultra 550B A55B
- Muse Glimmer 30B vs occamy-1.0
- Muse Glimmer 30B vs Olmo 3 7B Think
- Muse Glimmer 30B vs Ornith-1.5-122B
- Muse Glimmer 30B vs Ornith-1.5-35B-A3B
- Muse Glimmer 30B vs Ornith-1.5-397B
- Muse Glimmer 30B vs Ornith-1.5-9B
- Muse Glimmer 30B vs Qwen-AgentWorld-35B-A3B
- Muse Glimmer 30B vs Qwen3-30B-A3B-Instruct-2507
- Muse Glimmer 30B vs Qwen3-4B-Instruct-2507
- Muse Glimmer 30B vs Qwen3.5-0.8B
- Muse Glimmer 30B vs Qwen3.5-122B-A10B
- Muse Glimmer 30B vs Qwen3.5-2B
- Muse Glimmer 30B vs Qwen3.5-397B-A17B
- Muse Glimmer 30B vs Qwen3.5-4B
- Muse Glimmer 30B vs Qwen3.5-9B
- Muse Glimmer 30B vs Qwen3.6-27B
- Muse Glimmer 30B vs Qwen3.6-35B-A3B
- Muse Glimmer 30B vs Qwen3.8-27B
- Muse Glimmer 30B vs Qwen3.8-Flash-Next
- Muse Glimmer 30B vs Qwen3-Coder-30B-A3B-Instruct
- Muse Glimmer 30B vs Qwen3-Coder-Next
- Muse Glimmer 30B vs Qwen3-Omni-30B-A3B-Instruct
- Muse Glimmer 30B vs Qwen3-VL-2B-Instruct
- Muse Glimmer 30B vs Qwen3-VL-30B-A3B-Instruct
- Muse Glimmer 30B vs Qwen3-VL-32B-Instruct
- Muse Glimmer 30B vs Qwen3-VL-4B-Instruct
- Muse Glimmer 30B vs Qwen3-VL-8B-Instruct
- Muse Glimmer 30B vs Qwopus3.8-27B-Flash-V2
- Muse Glimmer 30B vs Recursive Flint
- Muse Glimmer 30B vs Ripple-65B Preview
- Muse Glimmer 30B vs SmolLM3-3B
- Muse Glimmer 30B vs Spark-X2.6-4B
- Muse Glimmer 30B vs Swift 1.5 Qwen3.8-27B
- Muse Glimmer 30B vs Swift 1.5 Qwen3.8-Flash-Next
- Muse Glimmer 30B vs ThinkingCap (Qwen3.8 27B)
- Muse Glimmer 30B vs Baidu Unlimited-OCR-2
Machine-readable
- This page as Markdown
/compare/granite-4-2-8b-vs-muse-glimmer-30b.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/muse-glimmer-30b.json - From a terminal
anchor compare granite-4-2-8b muse-glimmer-30b(the CLI) - Over MCP
compare_tools {"a": "granite-4-2-8b", "b": "muse-glimmer-30b"}at/mcp, no key