--- title: DeepSeek-V4.1-Flash-DSpark-4d2e-MLX canonical_url: "https://www.modelscope.ai/models/rapid-mlx/DeepSeek-V4.1-Flash-DSpark-4d2e-MLX" md_url: "https://www.modelscope.ai/models/rapid-mlx/DeepSeek-V4.1-Flash-DSpark-4d2e-MLX.md" repository: rapid-mlx/DeepSeek-V4.1-Flash-DSpark-4d2e-MLX last_updated: 2026-10-15 license: mit pipeline_tag: text-generation tasks: - text-generation model_type: - deepseek_v41 architectures: - DeepseekV41ForCausalLM base_model: - deepseek-ai/DeepSeek-V4.1-Flash - rapid-mlx/DeepSeek-V4.1-Flash-REAP-2bit-MLX base_model_relation: quantized parameters: 1.4B tensor_type: - U32 - F32 - BF16 library_name: - mlx - safetensors - pytorch frameworks: - pytorch downloads: 85 stars: 0 tags: - mlx - deepseek - speculative-decoding - multi-token-prediction - apple-silicon - rapid-mlx --- # DeepSeek-V4.1-Flash-DSpark-4d2e-MLX > DeepSeek-V4.1-Flash-DSpark-4d2e-MLX - An open-source model by rapid-mlx on ModelScope. Run the paired model on your Mac rapid-mlx/DeepSeek-V4.1-Flash-DSpark-4d2e-MLX is a 1.4B-parameter text-generation model on ModelScope. licensed under mit. derived from deepseek-ai/DeepSeek-V4.1-Flash、rapid-mlx/DeepSeek-V4.1-Flash-REAP-2bit-MLX. - **Repository**: rapid-mlx/DeepSeek-V4.1-Flash-DSpark-4d2e-MLX - **License**: mit - **Tasks**: text-generation - **Parameters**: 1.4B - **Base model**: deepseek-ai/DeepSeek-V4.1-Flash, rapid-mlx/DeepSeek-V4.1-Flash-REAP-2bit-MLX - **Tags**: mlx, deepseek, speculative-decoding, multi-token-prediction, apple-silicon, rapid-mlx - **Downloads**: 85 - **Stars**: 0 - **Last updated**: 2026-10-15 Source: https://www.modelscope.ai/models/rapid-mlx/DeepSeek-V4.1-Flash-DSpark-4d2e-MLX --- ## Run the paired model on your Mac This repository is a sidecar, not a standalone model. The command serves its paired target and uses this sidecar. ```bash curl -fsSL https://rapidmlx.com/install.sh | bash rapid-mlx serve deepseek-v41-flash-reap-2bit curl -s http://localhost:8000/v1/chat/completions -H 'Content-Type: application/json' -d '{"model":"default","messages":[{"role":"user","content":"Say hello"}]}' ``` Use it from OpenCode / Claude Code / Codex: `rapid-mlx agents --setup` · [Agent setup](https://rapidmlx.com/docs/agents) [Download the Desktop app](https://rapidmlx.com/download) · 256 GB unified memory required for the paired 212.9 GB target plus this 4.6 GB sidecar. This repo alone cannot answer prompts. # DeepSeek V4.1 Flash DSpark 4d2e MLX Experimental three-stage DSpark speculative-decoding sidecar for the Rapid-MLX DeepSeek V4.1 Flash REAP 2-bit target. ## This is a sidecar, not a standalone model This repository contains only the 4.62 GB DSpark head. It cannot generate text by itself and does not contain the approximately 213 GB target model. Required target: - Repository: `rapid-mlx/DeepSeek-V4.1-Flash-REAP-2bit-MLX` - Qualified target revision: `a25fec277b9e7cedc0e9f3f15da874a5cf9d491b` - Runtime: Rapid-MLX's owned DeepSeek V4.1 DSpark implementation - Recommended verification window: **K=4** - Minimum supported machine class: **256 GiB unified memory** Rapid-MLX downloads and verifies this sidecar separately when its experimental DSpark path is enabled. Users who do not enable DSpark do not need these files. ## Precision layout `4d2e` means: - Attention, shared-expert, main-projection, Markov, and confidence paths: affine 4-bit, group size 64 - Bandwidth-dominant routed experts: affine 2-bit, group size 64 - Target-shared embedding and LM head: provided by the 2-bit target at runtime The mixed layout is 4,617,792,648 bytes, only 3.5% larger than the fully 2-bit DSpark head. A uniform 4-bit head was not viable inside the qualified 256 GiB memory boundary. ## Measured performance Environment: - Apple M3 Ultra, 256 GiB unified memory - Target: REAP12.5 native affine 2-bit checkpoint, approximately 212.93 GB - Rapid-MLX packed DSpark verification, K=4 - Four prompt domains: code, arithmetic reasoning, JSON-only structured output, and Chinese - Up to 128 output tokens, two consecutive repeats per prompt | Path | Weighted decode throughput | Relative to AR | | --- | ---: | ---: | | Target autoregressive | 9.58 tok/s | 1.00x | | Mixed DSpark, K=4 | **19.39 tok/s** | **2.02x** | | Mixed DSpark, K=5 | 18.49 tok/s | 1.93x | The K=4 result is approximately 20 tok/s for this measured configuration; it is not a guarantee for every prompt, context length, thermal state, or machine. Per-domain K=4 results ranged from 11.87 to 25.93 tok/s. Mean accepted draft length was 1.85 extra tokens per verification block. Peak MLX memory was 218.232 GB. K=5 accepted more draft tokens but was slower end to end, so K=4 is the qualified fixed-window setting. ## Correctness and experimental status All four K=4 outputs were token-for-token stable across two repetitions. The verifier is target-authoritative: draft tokens are emitted only after target verification, and corrections come from target logits. Fixed-batch speculative output is not promised to be bitwise identical to a sequential autoregressive run. Low-margin target decisions can differ with the verification batch shape. The current 2-bit target also showed weak or repetitive instruction-following on several English probes. Treat this sidecar as experimental while broader comparative task-quality qualification is in progress. ## Artifact integrity The manifest records the immutable source revisions and shard hashes. Rapid-MLX pins the repository revision and independently validates every required file's size and SHA-256 before loading it. | File | Bytes | SHA-256 | | --- | ---: | --- | | `dspark-mixed-stage-0.safetensors` | 1,556,346,856 | `381a7fbc8758cd86baab55e8f1ae3020e49e2977f067d4269416889c1aee8118` | | `dspark-mixed-stage-1.safetensors` | 1,512,099,424 | `2ca7dc77528ebe3220e6e1633733925ca3420e346b4475163e1639541333876e` | | `dspark-mixed-stage-2.safetensors` | 1,549,346,368 | `1ed4663f0487e13372e753b2a5e8b760ae8fd43ba661fae891dfdff62384e64b` | | `config.json` | 138,476 | `3518b608fd8b90bc518c7d4533c751367fe3c2416aa3a4f7fde40bc6e498f012` | | `model.safetensors.index.json` | 265,016 | `70cbf70324c1b8d7d7c3d5f7f522f38d0be6cba673e90430a0f9a1d8b1ab8cff` | ## Sources and license The dense DSpark paths were converted from the official DeepSeek V4.1 Flash release at revision `dba1be0a40aa45a94ad051997016db3960a90277`. Routed expert values come from the pinned affine 2-bit source at revision `802f1a00982705d81b79ad1c83aa0ccc0b863ebc`. This repository is distributed under the MIT license. See `LICENSE` and `NOTICE`.