LocalClaw/LLM/Ripple 65B Preview
Open-weight local LLM

Ripple 65B Preview

Use case: Reasoning. Check the memory fit and choose a setup path below.

48 GB short-context planning estimate48 GB RAMAD-Q4_K_MReasoning
Choose an app

This model needs a special runtime. Unsupported apps are clearly marked.

Compare models
LM StudioNot available for this model
UnslothNot available for this model
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloads
llama.cppNot available for this model
Use with LocalClawOptional workspace after the model is installed
This model needs its official runtimellama.cpp containing fecdc81eec0922b229e7e6f4069cea603e10d6a7 (PR 31692); use --jinja -c 4096; LM Studio/Ollama support not confirmed
Parameters
65B
RAM planning estimate
48 GB
Model size
40.43 GB
Quantization
AD-Q4_K_M

About Ripple 65B Preview

Catalogue summary: Ricursive Intelligence dense model pretrained from scratch for agentic coding. AtomicChat AD-Q4_K_M GGUF is 40.43GB; its publisher recommends 48GB memory for moderate context. Requires llama.cpp with merged Ripple support; start at 4096 tokens.

Ripple 65B Preview has a 48 GB short-context RAM planning estimate based on its 40.43 GB GGUF. This is not a measured minimum or a guarantee at maximum context.

Use the official llama.cpp containing fecdc81eec0922b229e7e6f4069cea603e10d6a7 (PR 31692); use --jinja -c 4096; LM Studio/Ollama support not confirmed setup. The current low-bit files are not a stock LM Studio install.

Model sourcePublic GGUF repository (verified 2026-11-06): AtomicChat/Ripple-65B-Preview-GGUFUpstream releaseLicence text
codingreasoningtool-callinglong-contextpower

Install path

01
Check RAM fitPlan for 48 GB RAM at short context; this is an estimate. Use AD-Q4_K_M.
02
Load the modelFollow the official llama.cpp containing fecdc81eec0922b229e7e6f4069cea603e10d6a7 (PR 31692); use --jinja -c 4096; LM Studio/Ollama support not confirmed instructions. Stock LM Studio support is not confirmed.
03
Try your workloadStart with a short prompt, check memory use and adjust context length before running longer tasks.

Download formats for this model

These are quantizations of the same model. The RAM fit above uses AD-Q4_K_M; larger files need more memory. File sizes exclude the runtime, context cache and optional vision projector.

Catalogue record

  • Family: ripple
  • Parameters: 65B
  • Recommended quantization: AD-Q4_K_M
  • Short-context RAM estimate: 48 GB
  • Catalogue model size: 40.43 GB
  • Tags: coding, reasoning, tool-calling, long-context, power

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Reading the scores

LocalClaw /10 is an editorial catalogue rating. Community /5 comes from member reviews. Your machine fit is a separate memory and runtime assessment.

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
?
quality
?
coding
?
reasoning
?

Technical notes

Developer
Ricursive Intelligence
License
Apache 2.0
Context window
1,048,576 tokens
Architecture
65B dense Transformer; 80 layers with sliding-window and global attention, attention gating and value residual connections.

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Workstation fitMac Studio M4 Max 64GBCUDA workstation classNVIDIA GB10 / DGX SparkLarge local models64GB RAM guide

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

KAT-Coder V2.5 Dev 35B (3B active, MoE)Nemotron 3.5 Lightning 30B-A3B 30B (3B active, MoE)Nex-N2.5-mini 35B MoEOccamy-1.0 35B (3B active, MoE)Qwen3-Coder-Next 80B (3B active, MoE)Xing4.0-29B-A4B 29B (4B active, MoE)LFM2.5-24B-A2B 24B (2.45B active, MoE)Kimi Linear 48B-A3B Instruct 48B (3B active, MoE)

Where to go next