LocalClaw/LLM/Ling Flash Base 2.0
Open-weight MoE

Ling Flash Base 2.0

Catalogue summary: InclusionAI MIT-licensed Ling 2.0 base MoE with about 106B total parameters, 6.1B active parameters and 32K context extendable toward 128K with YaRN. Practical local use requires the official Ling GGUF files and patched llama.cpp runtime.

Repository editorial metadata; verify comparative claims in the linked upstream material.

128 GB catalogue minimum128 GB RAMQ3_K_SCoding assistant
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 runtimeLing llama.cpp fork
Parameters
106B (6.1B active, MoE)
Minimum RAM
128 GB
Model size
46 GB
Quantization
Q3_K_S

Can Ling Flash Base 2.0 run locally?

Ling Flash Base 2.0 has a catalogue minimum of 128 GB RAM with Q3_K_S. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Treat ling-flash-base-2.0 as a server-grade catalogue target. Use the verified artefact with a compatible multi-GPU or distributed runtime and follow its upstream instructions; this is not a one-click desktop LM Studio recommendation.

Model sourcePublic GGUF repository (verified 2026-09-07): mradermacher/Ling-flash-base-2.0-GGUFUpstream releasePaper or model cardLicence text
chatcodereasoningpowerlong-contextmoe

Deployment path

01
Check RAM fitServer-grade target. Plan for 128 GB class multi-GPU memory.
02
Load the modelUse ling-flash-base-2.0 only with a compatible server-grade or distributed runtime; confirm the exact artefact and upstream instructions first.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: ling
  • Parameters: 106B (6.1B active, MoE)
  • Recommended quantization: Q3_K_S
  • Catalogue minimum RAM: 128 GB
  • Catalogue model size: 46 GB
  • Tags: chat, code, reasoning, power, long-context, moe

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.

Catalogue tags

  • chat
  • code
  • reasoning
  • power
  • long-context
  • moe

Capability profile

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

speed
5
quality
9
coding
9
reasoning
9

Technical notes

Developer
InclusionAI
License
MIT
Context window
32,768 tokens
Architecture
BailingMoeV2 sparse MoE causal language model with about 106B total parameters, 6.1B active parameters, 256 experts and 8 routed experts per token. The model card describes 32K native context and YaRN extrapolation toward 128K.

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.

Large unified memoryMac Studio M4 Max 128GB128GB AI PC classNVIDIA GB10 / DGX SparkHigh-memory picks128GB RAM guide

Related catalogue entries

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

Ling-2.6-flash (104B MoE) 104B (7.4B active)Ling-3.0-tiny 7.9B (1.3B active, MoE)LongCat-Flash-Lite 68.5B (3-4.5B active, MoE)Qwen3-Coder-Next 80B (3B active, MoE)K2-Horizon-MoVA-36B-A4B 36B (4B active, MoE)Mistral Small 4 (119B-A6.5B) 119B (6.5B active, MoE)DeepSeek V4 Flash Vision Exp 284B (13B active, multimodal MoE)Kimi Linear 48B-A3B Instruct 48B (3B active, MoE)

Where to go next