Models / Olmo Hybridgenerated from capability-matrix.json
Olmo Hybrid
Ai2's 7B hybrid: mostly linear-attention layers, a few full-attention ones, no position encoding at all.
chatsafetensors
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
- 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 the released 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)
full-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
- olmo_hybrid
- design
- gated-linear hybrid (Gated DeltaNet)
- experts
- dense
- attention window
- none
- QK-norm
- yes
- RoPE
- none
- norm
- RMSNorm, post-only
- activation
- SwiGLU
- tied head
- no
- modality
- text
- GPU-resident
- eligible
registry description: Ai2 Olmo Hybrid (7B): qwen3.5's Gated DeltaNet (3:1) + olmo3's own full-attention shape, MIXED norm placement per layer kind, no RoPE at all