LocalFit

Hy4-preview

tencent/Hy4-preview

Released2026-08-28Size770B · 49B activeLicenseapache-2.0

Files and memory at 8K context

QuantFileFiles+ KV + runtimeSmallest fitSource
Q4_K_M
AngelSlim/Hy4-preview-GGUF
435 GiB1unknownover 192 GB GPUHF files
MLX 4-bit
mlx-community/Hy4-preview-4bit
404 GiB103unknownover 512 GB MacHF files

No verified file: Q5_K_M, Q8_0, FP16, BF16, MLX 8-bit. Sizes are exact file bytes (text weights; projectors listed separately). “+” = recurrent state or other terms unknown. Smallest fit adds 0.5 GiB spare; Macs use 75% of memory.

Quality

Artificial Analysis Intelligence Index

Unknown

Arena text rating

Unknown

Scores describe the evaluated hosted variant, not each quantized file. AA and Arena are never averaged.

Reported speeds 0

No reported measurement yet. Submit one.