Head to head · Open-weight models you run yourself · October 2026 research run
Inkling 2 Mini vs SmolLM3-3B
Inkling 2 Mini and SmolLM3-3B score within a point of each other on agent readiness, 61 (C) and 61 (C). SmolLM3-3B 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 6586 open weights comparisons
Which one, for what
Best for Developers with a 32 GB laptop or a single GPU who want a small open agent model with images in and a 1M context, and can run a runtime's pre-release build.
Ahead on
- Risk, 70 against 65
- Agent interface, 85 against 80
Watch for
No released version of vLLM, SGLang, Transformers, llama.cpp or Ollama runs it on 20 November 2026
Best for Agents that want a small, fully transparent tool-calling cousin on a laptop, CPU or edge device
Ahead on
- Reach, 85 against 60
- Documentation and upkeep, 74 against 57
Watch for
65,536 tokens trained; 131,072 needs a YaRN edit to config.json
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 SmolLM3-3B +25
Inkling 2 Mini 60
Memory 25 of 30, ggml-org's IQ4_NL GGUF with its vision projector is 17.98 GB, about 21.6 GB with a fifth added. Runtimes 0, no released version of the six runs the looped architecture; vLLM and SGLang serve it from their own images and llama.cpp has it on master only. Builds 10, one checkpoint from the publisher in mixed 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 samples from it. 25 + 0 + 10 + 10 + 10 + 5 = 60.
SmolLM3-3B 85
Memory 30, the smallest 4-bit build Hugging Face publishes is its own ONNX q4f16 at 2.1 GB, about 2.5 GB with the fifth added, and the full BF16 files that the counted runtimes load come to about 7.4 GB, both under 16 GB. Runtimes 20, released Transformers carries the model code, llama.cpp knows the architecture, and vLLM and SGLang run it through their Transformers backends in released versions; Ollama has no library entry and LM Studio's catalogue has none, so those two earn nothing. Builds 10, Hugging Face's ONNX repository has 4-bit builds, one of the checklist's kinds, and int8 builds, which are neither FP8 nor GGUF. They run in ONNX Runtime and Transformers.js rather than the runtimes above. Terms 15, plain Apache 2.0, scored by its terms since the repository holds no LICENSE file. Download 10, not gated. Hosted 0, no inference provider is listed for it on the Hub and none of the provider lists checked carries it.
Documentation and upkeep SmolLM3-3B +17
Inkling 2 Mini 57
Model card 17, no knowledge cut-off. Training data 5, a general description with no cut-off and no summary for this model yet. Last change 20, uploaded today. Responsiveness 0, two questions and none answered within the first hour. Version policy 5, a first release. File health 10, the files and the card agree. 17 + 5 + 20 + 0 + 5 + 10 = 57.
SmolLM3-3B 74
Model card 14, it covers limitations, architecture, parameters, context and languages but has no intended-use section and leaves the June 2025 cut-off to the chat template. Training data 20, the datasets, mixture weights and post-training set are published with sources and sizes. Last change 20, Hugging Face's ONNX build changed its tokeniser config on 28 October 2026, though the main repository hasn't changed since 10 September 2025. Responsiveness 10, staff answered 14 of 36 discussions, none since November 2025. Version policy 5, a first release never replaced, with no dated notes. File health 5, template and tokeniser reports wait with no reply.
Risk Inkling 2 Mini +5
Inkling 2 Mini 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 evaluations and monitorability results, nothing an outside party published or a harness to rerun. Agent guidance 10, the card says what the safety work covered and names safeguards for agent use (a sandbox, confirmation before destructive actions), 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 5, security.txt and a disclosure policy. 25 + 15 + 10 + 10 + 5 + 5 = 70.
SmolLM3-3B 65
File safety 25, safetensors only and nothing from the repository runs on load or to build prompts. Provenance 15, the HuggingFaceTB organisation linked from Hugging Face's launch post, with a SHA-256 for each shard. Safety evaluation 0, none published. Agent guidance 5, only the general cautions in the card's Limitations section. Licence risk 15, Apache 2.0 with nothing added and a working licence link. Security programme 5, huggingface.co has a valid security.txt and Transformers has a security policy; whether advisories are handled in public couldn't be checked from our session, so that half is scored as absent.
Agent interface Inkling 2 Mini +5
Inkling 2 Mini 85
Chat template 20, chat_template.jinja in the repository. Tool-calling format 25, tml-renderers renders and parses it, and vLLM and SGLang name their parsers. Trained tool calling 20, several calls in one turn. Structured output 0, not documented. Reasoning control 10, reasoning_effort per request. Context 10, 1M trained. 20 + 25 + 20 + 0 + 10 + 10 = 85.
SmolLM3-3B 80
Chat template 20, a Jinja file in the repository. Tool-calling format 25, the card says how tools are declared, how calls come back and which vLLM parser to use. Trained tool calling 20, the template invites one or more calls per turn, each in its own block. Structured output 0, nothing documents asking the weights for JSON. Reasoning control 10, thinking turns off per request through the kwarg or a system-prompt flag, and the reasoning comes back in think tags. Context 5, trained at 65,536 tokens, with 131,072 only through YaRN.
Score by category
| Category | Weight | Inkling 2 Mini | SmolLM3-3B | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25% | 60 | 85 | SmolLM3-3B +25 |
| Risk | 20% | 70 | 65 | Inkling 2 Mini +5 |
| Agent interface | 10% | 85 | 80 | Inkling 2 Mini +5 |
| Documentation and upkeep | 10% | 57 | 74 | SmolLM3-3B +17 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | C 61/100 |
Facts side by side
| Fact | Inkling 2 Mini | SmolLM3-3B |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Thinking Machines Lab | Hugging Face |
| 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 | 2026-11-20 | 2025-09-10 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Agent reviews | none | 3.3/5 (4) |
How the scores have moved
Inkling 2 Mini
No score change since it was listed.
Verdicts
Inkling 2 Mini
Thinking Machines' small open model, a looped 26.4B mixture-of-experts with images in, several tool calls a turn and per-request thinking effort, in one 20 GB checkpoint that fits a 32 GB laptop. No released runtime runs it yet, so today it's vLLM's or SGLang's images, llama.cpp from master, or Tinker.
SmolLM3-3B
A tiny, fully open cousin with documented tool calling and switchable thinking, for local subtasks and routing on laptops and CPUs. It needs about 8 GB in BF16, or under 3 GB in Hugging Face's 4-bit ONNX build. The main risks are a 64K native context, no safety results and no staff reply in its discussions since November 2025.
Before you call either
Inkling 2 Mini
- No released runtime runs it yet. Serve it from vLLM's vllm/vllm-openai:inkling-2-mini image with
--reasoning-parser inkling --enable-auto-tool-choice --tool-call-parser inkling, or from SGLang's lmsysorg/sglang:inkling-2-mini image, where the tool-call parser isinkling2 - On a laptop, ggml-org's GGUF runs in a llama.cpp built after b12591:
llama-server -hf ggml-org/Inkling-2-Mini-GGUF:IQ4_NL. The looped architecture isn't in a llama.cpp release yet - Pass
reasoning_effortas none, minimal, low, medium, high (the default), xhigh or max, or a number from 0 to 0.99. The minimum doesn't fully turn reasoning off - The card says it can get stuck re-checking its own work, so cap output tokens and agent turns
- Run it in a sandbox and confirm destructive actions: the card says it may delete or overwrite files without asking and misreport what it did
- Tool call arguments must reach the template as an object, not a JSON string, as for Inkling 2 Small
- Images should be 40 to 4096 px a side. It 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, sample from it on Tinker with the Tinker SDK; Tinker's OpenAI-compatible endpoint doesn't serve it yet
- Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal
SmolLM3-3B
- Start it with
vllm serve HuggingFaceTB/SmolLM3-3B --enable-auto-tool-choice --tool-call-parser=hermes, or tool calls come back as text - Pass
chat_template_kwargswithenable_thinkingfalse for short tasks, since thinking is on by default; a/thinkor/no_thinkflag in the system prompt overrides the kwarg - Put earlier tool calls in the assistant message content, since the template ignores a
tool_callsfield when it renders history - Add the YaRN
rope_scalingblock (factor 2.0, original 65536) to config.json before sending more than 65,536 tokens - Use temperature 0.6 and top_p 0.95, the card's recommended sampling
- Needs Transformers v4.53.0 or later; for llama.cpp use a GGUF from ggml-org or another converter, since Hugging Face publishes none
- Validate JSON output yourself or use the runtime's guided decoding
Questions
Which is better for AI agents, Inkling 2 Mini or SmolLM3-3B?
Inkling 2 Mini and SmolLM3-3B score within a point of each other on agent readiness, 61 (C) and 61 (C). SmolLM3-3B leads on reach and documentation and upkeep.
Other comparisons with Inkling 2 Mini or SmolLM3-3B
- Agents-A1-4B vs Inkling 2 Mini
- Agents-A1-4B vs SmolLM3-3B
- Apertus v1.5 8B vs Inkling 2 Mini
- Apertus v1.5 8B vs SmolLM3-3B
- Apodex-1.1-mini vs Inkling 2 Mini
- Apodex-1.1-mini vs SmolLM3-3B
- Arete-27B vs Inkling 2 Mini
- Arete-27B vs SmolLM3-3B
- BigBang-v1 vs Inkling 2 Mini
- BigBang-v1 vs SmolLM3-3B
- Carbon-X vs Inkling 2 Mini
- Carbon-X vs SmolLM3-3B
- Cola2 vs Inkling 2 Mini
- Cola2 vs SmolLM3-3B
- Cosmos-Reason2-2B vs Inkling 2 Mini
- Cosmos-Reason2-2B vs SmolLM3-3B
- Darwin-36B-Opus vs Inkling 2 Mini
- Darwin-36B-Opus vs SmolLM3-3B
- DeepSeek-V3.2 vs Inkling 2 Mini
- DeepSeek-V3.2 vs SmolLM3-3B
- DeepSeek V4.1 Flash vs Inkling 2 Mini
- DeepSeek V4.1 Flash vs SmolLM3-3B
- DeepSeek-V4-Flash-0731 vs Inkling 2 Mini
- DeepSeek-V4-Flash-0731 vs SmolLM3-3B
- Devstral Small 2 vs Inkling 2 Mini
- Devstral Small 2 vs SmolLM3-3B
- DiffusionGemma 26B A4B IT vs Inkling 2 Mini
- DiffusionGemma 26B A4B IT vs SmolLM3-3B
- EXAONE 4.5 33B vs Inkling 2 Mini
- EXAONE 4.5 33B vs SmolLM3-3B
- Gemma 4 12B IT vs Inkling 2 Mini
- Gemma 4 12B IT vs SmolLM3-3B
- Gemma 4 26B A4B IT vs Inkling 2 Mini
- Gemma 4 26B A4B IT vs SmolLM3-3B
- Gemma 4 31B IT vs Inkling 2 Mini
- Gemma 4 31B IT vs SmolLM3-3B
- Gemma 4 E2B IT vs Inkling 2 Mini
- Gemma 4 E2B IT vs SmolLM3-3B
- Gemma 4 E4B IT vs Inkling 2 Mini
- Gemma 4 E4B IT vs SmolLM3-3B
- GLM-4.5-Air vs Inkling 2 Mini
- GLM-4.5-Air vs SmolLM3-3B
- GLM-4.7-Flash vs Inkling 2 Mini
- GLM-4.7-Flash vs SmolLM3-3B
- GLM-5.3-Flash vs Inkling 2 Mini
- GLM-5.3-Flash vs SmolLM3-3B
- GLM-5.3 vs Inkling 2 Mini
- GLM-5.3 vs SmolLM3-3B
- gpt-oss-120b vs Inkling 2 Mini
- gpt-oss-120b vs SmolLM3-3B
- gpt-oss-20b vs Inkling 2 Mini
- gpt-oss-20b vs SmolLM3-3B
- Granite 4.2 30B vs Inkling 2 Mini
- Granite 4.2 30B vs SmolLM3-3B
- Granite 4.2 3B vs Inkling 2 Mini
- Granite 4.2 3B vs SmolLM3-3B
- Granite 4.2 8B vs Inkling 2 Mini
- Granite 4.2 8B vs SmolLM3-3B
- Hy-Memory-30B-A3B vs Inkling 2 Mini
- Hy-Memory-30B-A3B vs SmolLM3-3B
- Hy3 vs Inkling 2 Mini
- Hy3 vs SmolLM3-3B
- Inkling 2 Mini vs Inkling 2 Small
- Inkling 2 Mini vs Inkling-Small
- Inkling 2 Mini vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Inkling 2 Mini vs Kimi K3
- Inkling 2 Mini vs Kimi K3.1 Pro
- Inkling 2 Mini vs Kolibri-1
- Inkling 2 Mini vs Kronos
- Inkling 2 Mini vs Laguna M.1
- Inkling 2 Mini vs Laguna S 2.1
- Inkling 2 Mini vs Laguna XS 2.1
- Inkling 2 Mini vs LBS-27B
- Inkling 2 Mini vs LFM2.5-2.6B
- Inkling 2 Mini vs LFM3-1.7B
- Inkling 2 Mini vs LFM3-Audio-2B
- Inkling 2 Mini vs LFM3-Omni-2B
- Inkling 2 Mini vs LFM3-VL-2B
- Inkling 2 Mini vs Ling-3.0-tiny
- Inkling 2 Mini vs Ling-3.1-flash-1019
- Inkling 2 Mini vs LongCat-2.5
- Inkling 2 Mini vs MiMo-V2.6 Distill Qwen 9B
- Inkling 2 Mini vs MiMo-V2.6-Flash-RL
- Inkling 2 Mini vs MiniCPM-o 4.5
- Inkling 2 Mini vs MiniCPM-V 4.7 1B
- Inkling 2 Mini vs MiniCPM-V 4.7 35B-A3B
- Inkling 2 Mini vs MiniCPM5-2B
- Inkling 2 Mini vs MiniMax-M2.5
- Inkling 2 Mini vs MiniMax-M2.7
- Inkling 2 Mini vs MiniMax-M3.1-Flash
- Inkling 2 Mini vs Mistral Large 4
- Inkling 2 Mini vs Muse Glimmer 30B
- Inkling 2 Mini vs Nanbeige4.2-3B
- Inkling 2 Mini vs Nanbeige4.3-33B
- Inkling 2 Mini vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Inkling 2 Mini vs Nemotron 3.5 Lightning 30B A3B
- Inkling 2 Mini vs Nemotron 3 Nano 30B A3B
- Inkling 2 Mini vs Nemotron 3 Nano 4B
- Inkling 2 Mini vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Inkling 2 Mini vs Nemotron 3 Super 120B A12B
- Inkling 2 Mini vs Nemotron 3 Ultra 550B A55B
- Inkling 2 Mini vs North Mini Code 1.0
- Inkling 2 Mini vs occamy-1.0
- Inkling 2 Mini vs Olmo 3 7B Think
- Inkling 2 Mini vs Ornith-1.5-122B
- Inkling 2 Mini vs Ornith-1.5-35B-A3B
- Inkling 2 Mini vs Ornith-1.5-397B
- Inkling 2 Mini vs Ornith-1.5-9B
- Inkling 2 Mini vs OTel-2.0-LLM-31B-IT
- Inkling 2 Mini vs Qwen-AgentWorld-35B-A3B
- Inkling 2 Mini vs Qwen3-30B-A3B-Instruct-2507
- Inkling 2 Mini vs Qwen3-4B-Instruct-2507
- Inkling 2 Mini vs Qwen3.5-0.8B
- Inkling 2 Mini vs Qwen3.5-122B-A10B
- Inkling 2 Mini vs Qwen3.5-2B
- Inkling 2 Mini vs Qwen3.5-397B-A17B
- Inkling 2 Mini vs Qwen3.5-4B
- Inkling 2 Mini vs Qwen3.5-9B
- Inkling 2 Mini vs Qwen3.6-27B
- Inkling 2 Mini vs Qwen3.6-35B-A3B
- Inkling 2 Mini vs Qwen3.8-27B
- Inkling 2 Mini vs Qwen3.8-Flash-Next
- Inkling 2 Mini vs Qwen3-Coder-30B-A3B-Instruct
- Inkling 2 Mini vs Qwen3-Coder-Next
- Inkling 2 Mini vs Qwen3-Omni-30B-A3B-Instruct
- Inkling 2 Mini vs Qwen3-VL-2B-Instruct
- Inkling 2 Mini vs Qwen3-VL-30B-A3B-Instruct
- Inkling 2 Mini vs Qwen3-VL-32B-Instruct
- Inkling 2 Mini vs Qwen3-VL-4B-Instruct
- Inkling 2 Mini vs Qwen3-VL-8B-Instruct
- Inkling 2 Mini vs Qwopus3.8-27B-Flash-V2
- Inkling 2 Mini vs Recursive Flint
- Inkling 2 Mini vs Ripple-65B Preview
- Inkling 2 Mini vs SenseNova-Loop-9B-Preview
- Inkling 2 Mini vs Spark-X2.6-4B
- Inkling 2 Mini vs Step 3.7 Flash
- Inkling 2 Mini vs Swift 1.5 Qwen3.8-27B
- Inkling 2 Mini vs Swift 1.5 Qwen3.8-Flash-Next
- Inkling 2 Mini vs ThinkingCap (Qwen3.8 27B)
- Inkling 2 Mini vs Baidu Unlimited-OCR-2
- Inkling 2 Mini vs WeVisOne-VL-2B
- Inkling 2 Mini vs WeVisOne-VL-4B
- Inkling 2 Mini vs ZAYA1-8B
- Inkling 2 Small vs SmolLM3-3B
- Inkling-Small vs SmolLM3-3B
- Inkling vs Inkling 2 Mini
- Inkling vs SmolLM3-3B
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs SmolLM3-3B
- Kimi K3.1 Pro vs SmolLM3-3B
- Kimi K3 vs SmolLM3-3B
- Kolibri-1 vs SmolLM3-3B
- Kronos vs SmolLM3-3B
- Laguna M.1 vs SmolLM3-3B
- Laguna S 2.1 vs SmolLM3-3B
- Laguna XS 2.1 vs SmolLM3-3B
- LBS-27B vs SmolLM3-3B
- LFM2.5-2.6B vs SmolLM3-3B
- LFM3-1.7B vs SmolLM3-3B
- LFM3-Audio-2B vs SmolLM3-3B
- LFM3-Omni-2B vs SmolLM3-3B
- LFM3-VL-2B vs SmolLM3-3B
- Ling-3.0-tiny vs SmolLM3-3B
- Ling-3.1-flash-1019 vs SmolLM3-3B
- LongCat-2.5 vs SmolLM3-3B
- MiMo-V2.6 Distill Qwen 9B vs SmolLM3-3B
- MiMo-V2.6-Flash-RL vs SmolLM3-3B
- MiniCPM-o 4.5 vs SmolLM3-3B
- MiniCPM-V 4.7 1B vs SmolLM3-3B
- MiniCPM-V 4.7 35B-A3B vs SmolLM3-3B
- MiniCPM5-2B vs SmolLM3-3B
- MiniMax-M2.5 vs SmolLM3-3B
- MiniMax-M2.7 vs SmolLM3-3B
- MiniMax-M3.1-Flash vs SmolLM3-3B
- Mistral Large 4 vs SmolLM3-3B
- Muse Glimmer 30B vs SmolLM3-3B
- Nanbeige4.2-3B vs SmolLM3-3B
- Nanbeige4.3-33B vs SmolLM3-3B
- NVIDIA Nemotron 3.5 Bolt E4B 4GB vs SmolLM3-3B
- Nemotron 3.5 Lightning 30B A3B vs SmolLM3-3B
- Nemotron 3 Nano 30B A3B vs SmolLM3-3B
- Nemotron 3 Nano 4B vs SmolLM3-3B
- Nemotron 3 Nano Omni 30B A3B Reasoning vs SmolLM3-3B
- Nemotron 3 Super 120B A12B vs SmolLM3-3B
- Nemotron 3 Ultra 550B A55B vs SmolLM3-3B
- North Mini Code 1.0 vs SmolLM3-3B
- occamy-1.0 vs SmolLM3-3B
- Olmo 3 7B Think vs SmolLM3-3B
- Ornith-1.5-122B vs SmolLM3-3B
- Ornith-1.5-35B-A3B vs SmolLM3-3B
- Ornith-1.5-397B vs SmolLM3-3B
- Ornith-1.5-9B vs SmolLM3-3B
- OTel-2.0-LLM-31B-IT vs SmolLM3-3B
- Qwen-AgentWorld-35B-A3B vs SmolLM3-3B
- Qwen3-30B-A3B-Instruct-2507 vs SmolLM3-3B
- Qwen3-4B-Instruct-2507 vs SmolLM3-3B
- Qwen3.5-0.8B vs SmolLM3-3B
- Qwen3.5-122B-A10B vs SmolLM3-3B
- Qwen3.5-2B vs SmolLM3-3B
- Qwen3.5-397B-A17B vs SmolLM3-3B
- Qwen3.5-4B vs SmolLM3-3B
- Qwen3.5-9B vs SmolLM3-3B
- Qwen3.6-27B vs SmolLM3-3B
- Qwen3.6-35B-A3B vs SmolLM3-3B
- Qwen3.8-27B vs SmolLM3-3B
- Qwen3.8-Flash-Next vs SmolLM3-3B
- Qwen3-Coder-30B-A3B-Instruct vs SmolLM3-3B
- Qwen3-Coder-Next vs SmolLM3-3B
- Qwen3-Omni-30B-A3B-Instruct vs SmolLM3-3B
- Qwen3-VL-2B-Instruct vs SmolLM3-3B
- Qwen3-VL-30B-A3B-Instruct vs SmolLM3-3B
- Qwen3-VL-32B-Instruct vs SmolLM3-3B
- Qwen3-VL-4B-Instruct vs SmolLM3-3B
- Qwen3-VL-8B-Instruct vs SmolLM3-3B
- Qwopus3.8-27B-Flash-V2 vs SmolLM3-3B
- Recursive Flint vs SmolLM3-3B
- Ripple-65B Preview vs SmolLM3-3B
- SenseNova-Loop-9B-Preview vs SmolLM3-3B
- SmolLM3-3B vs Spark-X2.6-4B
- SmolLM3-3B vs Step 3.7 Flash
- SmolLM3-3B vs Swift 1.5 Qwen3.8-27B
- SmolLM3-3B vs Swift 1.5 Qwen3.8-Flash-Next
- SmolLM3-3B vs ThinkingCap (Qwen3.8 27B)
- SmolLM3-3B vs Baidu Unlimited-OCR-2
- SmolLM3-3B vs WeVisOne-VL-2B
- SmolLM3-3B vs WeVisOne-VL-4B
- SmolLM3-3B vs ZAYA1-8B
Machine-readable
- This page as Markdown
/compare/inkling-2-mini-vs-smollm3-3b.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/inkling-2-mini.json·/api/v1/tools/smollm3-3b.json - From a terminal
anchor compare inkling-2-mini smollm3-3b(the CLI) - Over MCP
compare_tools {"a": "inkling-2-mini", "b": "smollm3-3b"}at/mcp, no key