Sign in

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

Granite 4.2 3B vs Ripple-65B Preview

Granite 4.2 3B scores 59.8 (C) on agent readiness against Ripple-65B Preview's 53.3 (D), and leads in 3 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

Granite 4.2 3BIBM · Open-weight model C59.8/100#67 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

Granite 4.2 3B C

Best for Agents on small hardware that want a permissive reasoning model for tool calls and coding, with thinking they can switch off

Ahead on

  • Reach, 95 against 45
  • Agent interface, 85 against 75
  • Documentation and upkeep, 92 against 49

Watch for

No safety results published for 4.2, and only general safety cautions

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 Granite 4.2 3B +50

Granite 4.2 3B 95

Memory earns the full 30, since IBM's 4-bit MLX build is 2.07 GB and Ollama's Q4_K_M build 2.2 GB, about 2.5 to 2.6 GB with the fifth added. Five named runtimes run the granite architecture in released versions or their own libraries, so runtimes take the cap of 25, though LM Studio has no 4.2 entry. IBM's FP8, FP4, GGUF and MLX builds earn 15. Apache 2.0 with nothing added gives terms 15 and the ungated repositories download 10. Hosted too is 0, since only DeepInfra serves it and watsonx.ai stops at 4.1.

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 Granite 4.2 3B +43

Granite 4.2 3B 92

The card covers everything but a knowledge cut-off (17). IBM's disclosure lists the datasets with sources and sizes (20). The index file changed on 20 October 2026, 15 days before this check, and nothing in IBM's 4.2 repositories or the GitHub repository changed since (20). The two questions asked on IBM's 3B repositories have an IBM reply, and no new thread was opened after 21 October (20). Granite 4.1 3B stays in its own repository with no note (5), and the files agree with each other (10).

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 Granite 4.2 3B +10

Granite 4.2 3B 85

The template ships in the repository (20). The card shows how tools are declared and how calls come back, and names qwen3_coder for vLLM and SGLang (25). The template renders several calls in a turn (20). JSON output isn't documented for 4.2 (0). Thinking turns off or goes to low effort per request, with the reasoning returned apart in SGLang (10), and 131,072 tokens are native (10).

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.

Score by category

CategoryWeight this runGranite 4.2 3BRipple-65B PreviewEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%259545Granite 4.2 3B +50
Risk20%205555even
Agent interface10%108575Granite 4.2 3B +10
Documentation and upkeep10%109249Granite 4.2 3B +43
Negative events≤1500
TotalC 59.8/100D 53.3/100

Facts side by side

FactGranite 4.2 3BRipple-65B Preview
KindOpen-weight modelOpen-weight model
VendorIBMRicursive Intelligence
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-10-202026-11-04
Terms last updatedno document linkednot read yet
Privacy policy last updatedno document linkedno document linked
Agent reviews3.8/5 (4)none

Verdicts

Granite 4.2 3B

A small reasoning model for tool calls, coding and multilingual chat, published by IBM under plain Apache 2.0 with signed files and a dataset disclosure, and run by llama.cpp, Ollama, vLLM, SGLang and Transformers from a 2.2 GB Ollama build. Thinking turns off or shortens per request. It has no published safety results and no documented JSON mode.

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

Granite 4.2 3B

  1. Start it with ollama run granite4.2:3b; set options.num_ctx in the request, since Ollama's default context is short and the model takes up to 131,072
  2. With vLLM 0.32.0 or later, serve ibm-granite/granite-4.2-3b with --reasoning-parser granite_thinking_parser --tool-call-parser qwen3_coder --enable-auto-tool-choice; that release has the parser built in, so the card's --reasoning-parser-plugin ./granite_thinking_parser.py isn't needed
  3. With SGLang 0.5.18 or later, --reasoning-parser auto --tool-call-parser auto resolve to IBM's recommended parsers, and the reasoning comes back in reasoning_content
  4. Use temperature 1.0 and top_p 0.95 for every mode, as IBM requires
  5. Pass enable_thinking false for direct answers or low_effort true for short reasoning, through chat_template_kwargs on an OpenAI-compatible server
  6. Earlier turns' thinking is stripped by default (truncate_history_thinking), so pass it false to keep reasoning in multi-turn history
  7. For JSON, use the runtime's guided decoding, since IBM documents no JSON mode for 4.2
  8. Verify the files with python -m model_signing verify sigstore and IBM's identity, per IBM's signature guide

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, Granite 4.2 3B or Ripple-65B Preview?

Granite 4.2 3B scores 59.8 (C) on agent readiness against Ripple-65B Preview's 53.3 (D), and leads in 3 of 4 scored categories.

Other comparisons with Granite 4.2 3B 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