---

license: mit

tags:

• deepseek
• deepseek-v4
• deepseek-v4-flash
• mixture-of-experts
• reap
• expert-pruning
• gguf
• ds4
• experimental
• dgx-spark

pipeline_tag: text-generation

---

DeepSeek V4 Flash — REAP K128 (Uniform)

REAP-pruned DeepSeek V4 Flash at K128 (128 routed experts per MoE layer).

Prunes 50% of routed experts via Cerebras REAP (Router-weighted Expert Activation Pruning),

preserving all attention, embeddings, shared experts, router, and MTP components.

Drop-in compatible with the standard ds4-engine runtime — uniform IQ2_XXS/Q2_K expert

quantization throughout all layers. No per-layer quant dispatch required.

At a Glance

| | |

|---|---|

| Base model | DeepSeek V4 Flash |

| Donor GGUF | antirez IQ2XXS-w2Q2K-AProjQ8 (80.8 GiB) |

| Pruning method | REAP (Cerebras Research) |

| Routed experts | 128 per layer (down from 256) |

| Kept slots | 5,888 / 11,008 |

| Hash-preserved | Layers 0-2 (256 experts each) |

| Pruned | Layers 3-42 (128 experts each) |

| Format | ds4-compact-v1 GGUF |

| File size | 46.98 GiB |

| Quantization | Uniform IQ2_XXS / Q2_K experts in all layers |

> This is the recommended variant for most users. Uniform expert quantization means

> it works out of the box with any ds4-engine build. The mixed-precision variant

> (52 GiB) has Q4_K in layers 37-42 but requires runtime per-layer quant dispatch.

Domain Split (Calibration)

8,000 prompts · 5.0M tokens · 1.3B routed expert observations

| Domain | Share |

|---|---|

| Coding & development | 35-40% |

| Agentic tool-calling | 16% |

| Research & knowledge | 15-20% |

| Math & science | 10-15% |

| Design & planning | 5-10% |

| Trivia & general QA | 3-5% |

Calibration used the REAP activation_energy_sum2 score metric with 4,096 token context per prompt.

Top-to-bottom expert score gap in layer 3: 2,200x (strong pruning signal).

How to Run

Requires eouya2/ds4-for-reaped (ds4 engine with compact GGUF support):

git clone https://github.com/eouya2/ds4-for-reaped
cd ds4-for-reaped
make cuda-spark -j$(nproc)  # DGX Spark / CUDA
# or: make                    # Metal / macOS

./ds4 --cuda -m DeepSeek-V4-Flash-REAP-K128-uniform.gguf --ctx 131072

API server mode:

./ds4-server --cuda -m DeepSeek-V4-Flash-REAP-K128-uniform.gguf \
  --host 0.0.0.0 --port 17777 --ctx 131072

How It Was Built

1. Donor GGUF: Downloaded antirez IQ2XXS-w2Q2K-AProjQ8 variant (80.8 GiB) — uniform IQ2_XXS/Q2_K experts throughout
2. Calibration: 8,000 prompts collected and run through ds4's imatrix collector on a DGX Spark (NVIDIA GB10) at 4,096 token context
3. REAP scoring: Imatrix activation data converted to per-expert REAP scores using activation_energy_sum2 (same calibration used for the mixed-precision variant — REAP scores are quantization-independent)
4. Pruning: 50% expert removal via ds4_prune_gguf.py from eouya2/reap-for-ds4. Layers 0-2 (hash-routed) preserved. Expert tensors copied byte-for-byte — no dequant/requant.
5. Output: ds4-compact-v1 GGUF

No fine-tuning. Purely structural expert removal. Weights are unmodified — a subset of the original experts.

Comparison with Mixed-Precision Variant

| | Uniform (this) | Mixed Precision |

|---|---|---|

| File size | 46.98 GiB | 52.04 GiB |

| Expert quants | IQ2_XXS/Q2_K all layers | Q4_K in layers 37-42 |

| Compatibility | Drop-in | Needs quant-aware runtime |

| Quality | Baseline | Slightly higher in deep layers |

Acknowledgments

• DeepSeek — DeepSeek V4 Flash base model
• antirez — ds4 engine and GGUF quants
• eouya2 — ds4-for-reaped and reap-for-ds4
• Cerebras Research — REAP (code)
• NVIDIA — DGX Spark hardware