DeepSeek-V4.1-Flash on local hardware
Estimated comfort for repository coding with Aider on a MacBook Pro M4 Pro 48GB.
DeepSeek-V4.1-FlashOpen source
deepseek-ai · mit · 1,367,081 downloads
Mixture of expertsVisionReasoning / thinking mode
- Parameters
- 763B exact
- Active per token
- ≈227B (6 of 384 experts)
- Context window
- 64K tokensRoPE-extended to 1M (quality degrades past native — treat long-context ratings as optimistic)
- Attention
- Sliding-window + global layers
- Layers · KV heads · head dim
- 40 · 1 · 512
- KV cache
- 0 KB/token · 0.0 GB at 32K
- Tool calling
- good (from chat template)
- Thinking
- good (from chat template)
- Vision
- good (from config)
- Commercial use
- allowedRetain the required license and attribution notices
- Import confidence
- medium · capabilities estimated
Weights by quantization
MXFP4
467 GB
gguf file size
- • Uses a compressed / sparse attention scheme; KV-cache size is approximate.
- • Context native 65536, rope-extended to 1048576 (yarn); quality degrades past native — treat long-context ratings as optimistic.
- • vision: good, inferred from config (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.
DeepSeek-V4.1-Flash — MXFP4
Does not fit in memory
Needs ≈386 GB but only ≈37 GB is available after the OS, other apps and Aider.
High confidence