---

license: apache-2.0

language:

- en

- zh

base_model:

- TaichuAI/ZDTaichu5.0-9B

- TaichuAI/ZDTaichu5.0-9B-DSpark

base_model_relation: quantized

pipeline_tag: text-generation

library_name: gguf

tags:

- gguf

- llama.cpp

- speculative-decoding

- draft-model

- dspark

- dflash

- zdtaichu5_0

- qwen3.5

- agent

---

ZDTaichu5.0-9B DSpark GGUF

GGUF files for ZDTaichu5.0-9B-DSpark, the official semi-autoregressive speculative decoding draft model developed by the Zi Dong Tai Chu team to accelerate ZDTaichu5.0-9B.

> [!NOTE]

> This is a speculative decoding draft model (D-Spark / DFlash), not a standalone general model. It must be paired with the primary ZDTaichu5.0-9B GGUF model during inference to increase generation speeds by up to 60–85%.

Benchmarks

!ZDTaichu5.0-9B benchmark results

Benchmark results reported by TaichuAI for the original ZDTaichu5.0-9B foundation model. These figures are not measurements of this GGUF conversion.

GGUF files

| Quantization | DSpark Draft File | Draft Size | Paired Base Model File |

| :--- | :--- | ---: | :--- |

| BF16 | ZDTaichu5.0-9B-DSpark-BF16.gguf | 4.40 GB | TaichuAI/ZDTaichu5.0-9B (Original Weights) |

| Q8_0 | ZDTaichu5.0-9B-DSpark-Q8_0.gguf | 2.34 GB | ZDTaichu5.0-9B-Q8_0.gguf (9.53 GB) |

| Q6_K | ZDTaichu5.0-9B-DSpark-Q6_K.gguf | 1.81 GB | ZDTaichu5.0-9B-Q6_K.gguf (7.36 GB) |

| Q5_K_M | ZDTaichu5.0-9B-DSpark-Q5_K_M.gguf | 1.67 GB | ZDTaichu5.0-9B-Q5_K_M.gguf (6.47 GB) |

| Q4_K_M | ZDTaichu5.0-9B-DSpark-Q4_K_M.gguf | 1.53 GB | ZDTaichu5.0-9B-Q4_K_M.gguf (5.63 GB) |

| Q4_0 | ZDTaichu5.0-9B-DSpark-Q4_0.gguf | 1.51 GB | ZDTaichu5.0-9B-Q4_0.gguf (5.31 GB) |

Draft model architecture

• Framework: DSpark (semi-autoregressive DFlash backbone + chained Markov head).
• Target Layers: Extracts auxiliary hidden states from target layers [1, 8, 15, 22, 29].
• Block Size: 8 tokens drafted per forward pass (dflash.block_size = 8).
• Target Model: ZDTaichu5.0-9B GGUF.

Usage

Use this draft model alongside the primary target model abenzerps/ZDTaichu5.0-9B-GGUF with llama.cpp (llama-cli or llama-server):

Text generation with Speculative Decoding (llama-cli)

llama-cli \
  -m ZDTaichu5.0-9B-Q4_K_M.gguf \
  -md ZDTaichu5.0-9B-DSpark-Q4_K_M.gguf \
  --spec-type draft-dspark \
  --spec-draft-n-max 8 \
  -c 8192 --jinja \
  --temp 0.7 --top-p 0.95 \
  -p "Explain why reproducible builds matter."

Multimodal vision understanding with Speculative Decoding (llama-cli)

llama-cli \
  -m ZDTaichu5.0-9B-Q4_K_M.gguf \
  -md ZDTaichu5.0-9B-DSpark-Q4_K_M.gguf \
  --mmproj mmproj-ZDTaichu5.0-9B-BF16.gguf \
  --spec-type draft-dspark \
  --spec-draft-n-max 8 \
  --image path/to/image.jpg \
  -p "Describe what is shown in this image in detail."

OpenAI-compatible server with Speculative Decoding (llama-server)

llama-server \
  -m ZDTaichu5.0-9B-Q4_K_M.gguf \
  -md ZDTaichu5.0-9B-DSpark-Q4_K_M.gguf \
  --mmproj mmproj-ZDTaichu5.0-9B-BF16.gguf \
  --spec-type draft-dspark \
  --spec-draft-n-max 8 \
  -c 8192 --jinja -fa on --host 0.0.0.0 --port 8080

Increase context -c up to 131,072 tokens (128K) when sufficient memory is available.

Source and build

• Source draft model: TaichuAI/ZDTaichu5.0-9B-DSpark
• Target base model: TaichuAI/ZDTaichu5.0-9B
• Conversion: ggml-org/llama.cpp commit 7ceed8737fdb4eb09b4760e77bd12d38012de5a8
• License: Apache-2.0
• Checksums: SHA256SUMS.txt