Models / Llama 4generated from capability-matrix.json
Llama 4
Meta's Llama 4 Scout and Maverick, text only.
chatexperts: sparse +sharedexperimentalsafetensors, GGUF
Get it
No vetted checkpoint yet. You can pull any GGUF of this family by repo and quant. goinfer checks it fits before downloading, but nobody here has timed it.
goinfer-chat pull <owner>/<repo>:<quant>What hasn't been shown
- Only checked against a small test model built from the same wiring, because no released Llama 4 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.
- 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 +coherent · what parity-gated means
Measured speed · decode, tokens per second
not measured — no vetted checkpoint to measure
Architecture, for the curious
- model_type
- llama4_text
- design
- softmax-GQA
- 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: Meta Llama 4 (Scout/Maverick) text decoder: iRoPE (RoPE/NoPE interleave) + L2 QK-norm + attn-temp + dense/MoE interleave (top-1 sigmoid + shared)