Ling-3.0-flash-GGUF

Ling-3.0-flash GGUF

GGUF quantized versions of inclusionAI/Ling-3.0-flash, a next-generation native hybrid reasoning model with 124B total parameters and 5.1B active parameters per token, supporting English and Chinese, with a 256K context window (extendable to 1M), tool-calling, and a built-in thinking/reasoning mode.

Model Overview

Ling-3.0-flash is a hybrid-linear MoE model built on a native hybrid linear attention architecture from the very start of pretraining, featuring 5:1 alternating stacking of Kimi Delta Attention (KDA) and Multi-Head Latent Attention (MLA), upgraded with KDA fine-grained diagonal gating and 1/64 sparse MoE. With 124B total parameters and 5.1B activated parameters per token, it achieves a synergistic leap in long-context efficiency and computational cost.

The model uses a Bailing V3-style conversation format with role-based delimiters (<role>SYSTEM</role>, <role>HUMAN</role>, <role>ASSISTANT</role>, <role>OBSERVATION</role>) separated by <|role_end|>. It supports special tokens for thinking/reasoning (controlled via detailed thinking on / detailed thinking off in the system prompt, with reasoning output between think/answer tokens) and tool calling (function blocks with parameter tags).

Model Architecture

Available GGUF Files

Recommended: Q4_K_M or Q5_K_M offer the best quality-to-size trade-off for most use cases.

Usage

llama.cpp CLI

./llama-cli \
  -m ling-3.0-flash-Q4_K_M.gguf \
  -p "Explain quantum computing in simple terms." \
  --temp 0.6 --top-p 0.95 --top-k 20

llama-server (OpenAI-compatible API)

./llama-server \
  -m ling-3.0-flash-Q4_K_M.gguf \
  --host 0.0.0.0 --port 8080

Thinking Mode

Thinking mode is enabled by default. The model outputs its reasoning between think and answer tokens before providing the final answer. To control thinking behavior, include detailed thinking on or detailed thinking off in the system prompt. When using an OpenAI-compatible API, you can also pass "chat_template_kwargs": {"enable_thinking": false} to disable thinking per request.

Tool Calling

The model supports function/tool calling. Tool definitions are injected into the system prompt within <tools></tools> XML tags, and the model responds with function blocks containing parameter elements. Tool results are returned via the observation role channel.

Generation Parameters

Recommended parameters from the original model:

Quantization

These GGUF files were created from the BF16 source model using llama-quantize from the llama.cpp project.

Acknowledgements

• Original model: inclusionAI/Ling-3.0-flash
• Quantization tool: llama.cpp

License

MIT License