Hy4-preview on local hardware
Estimated comfort for repository coding with Aider on a MacBook Pro M4 Pro 48GB.
Hy4-previewOpen source
tencent · apache-2.0 · 21,640 downloads
Mixture of expertsReasoning / thinking mode
- Parameters
- 780B exact
- Active per token
- ≈49B (8 of 256 experts)
- Context window
- 1M tokens
- Attention
- Multi-head latent attention (compressed KV)
- Layers · KV heads · head dim
- 78 · 8 · 64
- KV cache
- 88 KB/token · 2.7 GB at 32K
- Tool calling
- good (from chat template)
- Thinking
- good (from chat template)
- Vision
- basic (inferred — no supporting signal)
- Commercial use
- allowedRetain the required license and attribution notices
- Import confidence
- medium · capabilities estimated
Weights by quantization
Q4_K_M
435 GB
gguf file size
- • Uses a compressed / sparse attention scheme; KV-cache size is approximate.
- • vision: basic, inferred from missing signals (low confidence).
- • Capability ratings are estimated from model size and name — this model hasn't been assessed by hand.
- • GGUF sizes come from community conversions matched by model name; equivalence and runtime support are not verified. MLX conversion availability is unverified.
Hy4-preview — 4-bit
Does not fit in memory
Needs ≈417 GB but only ≈37 GB is available after the OS, other apps and Aider.
High confidence