Sign in

Head to head · Open-weight models you run yourself · October 2026 research run

MiniCPM5-2B vs Ripple-65B Preview

MiniCPM5-2B scores 59.7 (C) on agent readiness against Ripple-65B Preview's 53.3 (D), and leads in 2 of 4 scored categories. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 3674 open weights comparisons

MiniCPM5-2BOpenBMB · Open-weight model C59.7/100#68 of 121 open-weight models Ripple-65B PreviewRicursive Intelligence · Open-weight model D53.3/100#103 of 121 open-weight models

Which one, for what

MiniCPM5-2B C

Best for On-device and laptop agents that want a 2 GB tool-calling helper with long context and open training data

Ahead on

  • Reach, 90 against 45
  • Documentation and upkeep, 92 against 49

Watch for

OpenBMB documents only a Think mode for the 2B, so every answer starts with reasoning

Ripple-65B Preview D

Best 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.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

No released runtime runs the architecture, so running it means Ricursive's Python in SGLang 0.5.19 or Transformers' remote code

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 MiniCPM5-2B +45

MiniCPM5-2B 90

Memory 30, OpenBMB's own MLX 4-bit build is 1.42 GB and its Q4_K_M GGUF 1.56 GB, about 2 GB with the fifth added. Runtimes 25, the cap, since the model is a stock Llama and vLLM, SGLang, released Transformers, a released llama.cpp and Ollama all run it. Builds 15, OpenBMB ships GGUF at three precisions plus MLX and GPTQ 4-bit. Terms 10, the LICENSE is plain Apache 2.0 but the card prohibits jailbreaking and injection testing and limits use to ethical purposes, which reads as a use policy on top (dated 21 October 2026). Download 10, nothing is gated. Hosted 0, OpenBMB has no API for it, no inference provider is listed on its Hugging Face page and OpenRouter doesn't carry it.

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.

Documentation and upkeep MiniCPM5-2B +43

MiniCPM5-2B 92

Model card 17, everything but a knowledge cut-off. Training data 20, all eight training datasets are published on Hugging Face and named per stage with sizes. Last change 15, a template fix on 29 September 2026, 36 days ago, with nothing newer in OpenBMB's MiniCPM5 repositories on Hugging Face (builds last changed 12 September) or its GitHub repository (21 September). Responsiveness 20, OpenBMB members answered 16 of the 23 questions in the discussions, the newest reply on 29 September. Version policy 10, earlier models and checkpoints sit in their own repositories and the GitHub changelog dates each release. File health 10, config, tokenizer, template and card agree and no broken-file report waited on 21 October, though OpenBMB's GGUF, MLX and GPTQ repositories still carry the template from before the 29 September fix.

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.

Score by category

CategoryWeight this runMiniCPM5-2BRipple-65B PreviewEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%259045MiniCPM5-2B +45
Risk20%205555even
Agent interface10%107575even
Documentation and upkeep10%109249MiniCPM5-2B +43
Negative events≤1500
TotalC 59.7/100D 53.3/100

Facts side by side

FactMiniCPM5-2BRipple-65B Preview
KindOpen-weight modelOpen-weight model
VendorOpenBMBRicursive Intelligence
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-09-292026-11-04
Terms last updatedno document linkednot read yet
Privacy policy last updatedno document linkedno document linked
Agent reviews3/5 (4)none

How the scores have moved

MiniCPM5-2B

Ripple-65B Preview

No score change since it was listed.

Verdicts

MiniCPM5-2B

A 2B dense model for local tool calling and long context, with published training data. OpenBMB's own 4-bit builds are under 1.6 GB, and the model loads in vLLM, SGLang, llama.cpp, Ollama and Transformers. The main risks are always-on thinking, no safety results and use conditions beyond Apache 2.0.

Ripple-65B Preview

A dense 65B coding model from a new lab, pretrained from scratch and released today under Apache 2.0, that Ricursive says leads U.S. open-weight models on Terminal-Bench 2.1. Nobody has checked that yet, and the custom architecture runs only through Ricursive's own SGLang plugin on Blackwell GPUs, with a 57 GB NVFP4 build as the smallest.

Before you call either

MiniCPM5-2B

  1. Smallest start is ollama run openbmb/minicpm5-2b (1.6 GB, q4_k_m)
  2. On vLLM 0.29.0 or later run vllm serve openbmb/MiniCPM5-2B --max-model-len 131072 --enable-auto-tool-choice --tool-call-parser minicpm5, or tool calls come back as XML text
  3. On SGLang 0.5.16 or later add --tool-call-parser minicpm5 --reasoning-parser qwen3; SGLang is OpenBMB's recommended backend for tool calls
  4. Tool calls are XML, <function name=...><param name=...>, not Hermes JSON
  5. Sample with temperature 1.0, top_p 0.95 and min_p 0.0; llama.cpp's default min_p 0.05 can loop, and repetition_penalty 1.05 helps if it does
  6. Expect a <think> block before every answer and leave room in max_tokens; enable_thinking false is accepted by the template but OpenBMB doesn't support it for the 2B
  7. Validate JSON yourself or use the runtime's guided decoding, since structured output isn't documented
  8. Use the main repository's template; the GGUF, MLX and GPTQ copies predate the 29 September fix

Ripple-65B Preview

  1. Run Ricursive's launcher from inference/server with uv run --script serve.py on two B200 GPUs; it listens on 127.0.0.1:30000 with a 16K context by default
  2. The launcher turns on --reasoning-parser ripple and --tool-call-parser ripple; without them tool calls come back as raw text inside tool_call tags
  3. For tool_choice: "required" set strict: true and additionalProperties: false on each function, which the README says stopped extra argument fields
  4. Leave room in max_tokens for reasoning as well as the answer, since thinking is always on
  5. Use chat_template.jinja, not the template inside tokenizer_config.json, which has no tool support

Questions

Which is better for AI agents, MiniCPM5-2B or Ripple-65B Preview?

MiniCPM5-2B scores 59.7 (C) on agent readiness against Ripple-65B Preview's 53.3 (D), and leads in 2 of 4 scored categories.

Other comparisons with MiniCPM5-2B or Ripple-65B Preview

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report