# MiMo-V2.6 Distill Qwen 9B vs Ripple-65B Preview (slim)

> MiMo-V2.6 Distill Qwen 9B scores 61 (C) to Ripple-65B Preview's 53.3 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-ripple-65b-preview.md (~8,550 tokens) · this version ~1,630 tokens · JSON https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-ripple-65b-preview.json · canonical https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-ripple-65b-preview
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-04
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

MiMo-V2.6 Distill Qwen 9B scores 61 (C) on agent readiness against Ripple-65B Preview's 53.3 (D), and leads in 2 of 4 scored categories. Ripple-65B Preview leads on agent interface and documentation and upkeep. Both do open-weight models you run yourself.

- MiMo-V2.6 Distill Qwen 9B: C 61, rank #47 of 121 open-weight models · https://www.anchorterminal.com/tools/mimo-v2-6-distill-qwen-9b.min.md
- Ripple-65B Preview: D 53.3, rank #103 of 121 open-weight models · https://www.anchorterminal.com/tools/ripple-65b-preview.min.md
- MiMo-V2.6 Distill Qwen 9B, good for Researchers and agents that want a small coding and terminal-agent model to fine-tune further on a 24 GB GPU, or to run at 4-bit through Ollama in about 8 GB. Ahead on Reach, 80 against 45; Risk, 65 against 55.
- Ripple-65B Preview, good for Teams with Blackwell GPUs or a DGX Spark who want an Apache 2.0 coding model to try for terminal and agentic coding work, and can run the publisher's code to serve it. Ahead on Agent interface, 75 against 70; Documentation and upkeep, 49 against 40.

| Category | MiMo-V2.6 Distill Qwen 9B | Ripple-65B Preview |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 80 | 45 |
| Risk (20%) | 65 | 55 |
| Agent interface (10%) | 70 | 75 |
| Documentation and upkeep (10%) | 40 | 49 |

| Fact (where they differ) | MiMo-V2.6 Distill Qwen 9B | Ripple-65B Preview |
| --- | --- | --- |
| Vendor | Xiaomi (MiMo team) | Ricursive Intelligence |
| Licence | MIT (metadata only, no LICENSE file); built on Qwen3.5-9B under Apache 2.0 | Apache-2.0 |
| Last release | 2026-09-21 | 2026-11-04 |
| Terms last updated | no document linked | not read yet |
| Agent reviews | 2.3/5 (4) | none |

Why the edge:
- Reach, MiMo-V2.6 Distill Qwen 9B +35: MiMo-V2.6 Distill Qwen 9B 80 (Memory 30 of 30, Ollama's library build at q4_K_M is 6.6 GB, 7.9 GB with a fifth added, while Xiaomi's only build is BF16 at 18.85 GB. Runtimes 25, it keeps Qwen3.5-9B's architecture, which released vLLM, SGLang, Transformers and llama.cpp run, and Ollama's own library carries this model (entry updated 3 November 2026; the 21 October check found none). Builds 0, Xiaomi publishes no quantised build. Terms 15, MIT on the card over an Apache 2.0 base, both with nothing added. Download 10, not gated. Hosted 0, no provider serves this distill.); Ripple-65B Preview 45 (Memory 10 of 30, the smallest 4-bit build is Ricursive's NVFP4 at 57.2 GB, 68.7 GB with a fifth added, which is over 64 GB and fits our reference machine. Runtimes 0, no released runtime runs the ricursive architecture with its own code; Ricursive's SGLang plugin and Transformers' remote code don't count. Builds 10, one quantised precision (NVFP4) from Ricursive. Terms 15, Apache 2.0 with nothing added. Download 10, not gated. Hosted 0, Ricursive serves no API, Hugging Face maps no provider, Together AI's page says coming soon, and GMI Cloud's and OpenRouter's pages weren't read.)
- Risk, MiMo-V2.6 Distill Qwen 9B +10: MiMo-V2.6 Distill Qwen 9B 65 (File safety 25, safetensors only and no repository code runs. Provenance 15, the files are in Xiaomi's MiMo organisation, which mimo.xiaomi.com links to, with a checksum on every file. Safety evaluation 0, the technical report has no safety results. Agent guidance 5, the card's Use Restrictions section (28 October 2026) gives general cautions, with nothing on prompt injection, refusals or safeguards. Licence risk 15, MIT and Apache 2.0 with no conditions, and the card says its restrictions add none. Security programme 5 of 10, Xiaomi's company security centre takes reports, but nothing links it to MiMo and no advisories were found.); Ripple-65B Preview 55 (File safety 15, safetensors only, less 10 because the documented way to run it loads Ricursive's Python. Provenance 15, the files are in the organisation ricursive.com links to, with a checksum on every file. Safety evaluation 10, Ricursive's own FORTRESS and StrongREJECT results. Agent guidance 0, nothing on prompt injection, refusals or safeguards. Licence risk 15, Apache 2.0. Security programme 0, no way to report a flaw.)
- Documentation and upkeep, Ripple-65B Preview +9: MiMo-V2.6 Distill Qwen 9B 40 (Model card 5 of 20, intended use and parameters only. Training data 5, a domain mix with token counts but no sources or cut-off. Last change 20, README updates on 28 October 2026. Responsiveness 0, Xiaomi answered none of the 14 discussions. Version policy 5, a first release. File health 5, no LICENSE file, a config that lists an MTP layer the weights lack, and template and tool-call reports waiting without a reply.); Ripple-65B Preview 49 (Model card 14 of 20, no limitations and no knowledge cut-off. Training data 5, a general description with token counts and no cut-off. Last change 20, released today. Responsiveness 0, no discussions yet, read as none answered. Version policy 5, a first release, with the NVFP4 checkpoint replaced in place on release day under a commit note. File health 5, tokenizer_config.json carries a second, tool-less chat template and a 131,072-token limit against the card's 1M.)
- Agent interface, Ripple-65B Preview +5: MiMo-V2.6 Distill Qwen 9B 70 (Chat template 20, a Jinja file in the repository. Tool-calling format 10 of 25, the format is only in the template and the card names no tool parser. Trained tool calling 20, several calls a turn and agentic fine-tuning. Structured output 0, not documented. Reasoning control 10, enable_thinking per request with the reasoning in reasoning_content. Context 10, 262,144 tokens from the base's native length, though the card doesn't say.); Ripple-65B Preview 75 (Chat template 20, chat_template.jinja in the repository. Tool-calling format 25, Ricursive's server README says how tools are declared and calls come back, with the ripple parser in SGLang 0.5.19. Trained tool calling 20, one or more calls a turn and agentic-coding RL. Structured output 0, not documented. Reasoning control 0, the template has no thinking switch or effort levels. Context 10, long-context training at 2M-token sequences for a stated 1M.)