Models / Ling 3.0generated from capability-matrix.json
Ling 3.0
inclusionAI's Ling 3.0, tiny and flash.
chatexperts: sparse +sharedexperimentalsafetensors
Get it
goinfer can't fetch this one yet. Download the safetensors folder with your usual tool, then point goinfer at it.
goinfer-serve -model ./path/to/checkpoint-folderWhat hasn't been shown
- Only checked against a small test model built from the same wiring, because no released Ling 3.0 was small enough to run on the hardware available. Two families promoted past this stage turned out to have real bugs behind a passing fixture.
- Registered as experimental. It can change, or go, before v1.0.
- Runs on the CPU only today. Not eligible to live on a GPU.
- goinfer can't download it for you: this family only loads from safetensors, which come as several files. That's planned (checkpoint fetch, P1–P9).
- No vetted checkpoint, so there's no fit verdict, no speed and no tool-calling result for this family.
How sure we are
Against a small test model100.0%
picks the same next token as HuggingFace
1.00000
closest the raw scores get at their worst position (cosine, 1.00000 is identical; bar starts at 0.95)
experimental: tiny-oracle 100.0%/1.00000 · what parity-gated means
Measured speed · decode, tokens per second
not measured — no vetted checkpoint to measure
Architecture, for the curious
- model_type
- bailing_hybrid
- design
- latent-KV (MLA)
- experts
- sparse +shared
- attention window
- none
- QK-norm
- no
- RoPE
- full
- norm
- RMSNorm, pre-norm
- activation
- SwiGLU
- tied head
- no
- modality
- text
- GPU-resident
- no
registry description: inclusionAI Ling 3.0 (tiny/flash): DeepSeek-style MLA alternating with Kimi Delta Attention (per-channel-decay delta rule) every layer_group_size-th layer, over a DeepSeekMoE FFN