Total runs:
2.6M
Run Growth:
229.6K
Growth Rate:
9.27%
Sponsored by
Vmake Labs Video Enhancer
abenzerps / ZDTaichu5.0-9B-MLX-6bit
Model's Last Updated: September 16 2026
image-text-to-text
Introduction of ZDTaichu5.0-9B-MLX-6bit
Model Details of ZDTaichu5.0-9B-MLX-6bit
ZDTaichu5.0-9B MLX
MLX files for ZDTaichu5.0-9B , an advanced multimodal foundation model developed by the Zi Dong Tai Chu team for visual understanding, spatial reasoning, agentic tool use, and embodied AI workloads. Built on a Qwen3.5-9B language backbone and C-RADIOv4-H vision encoder, the source checkpoint supports a native context length of 131,072 tokens (128K) .
Benchmarks
Benchmark results reported by TaichuAI for the original ZDTaichu5.0-9B foundation model. These figures are not measurements of this MLX conversion.
MLX files
| Quantization | Repository | Size (GB) |
|---|---|---|
| 8-bit | ZDTaichu5.0-9B-MLX-8bit | 11.20 GB |
| 6-bit | ZDTaichu5.0-9B-MLX-6bit | 8.96 GB |
| 4-bit | ZDTaichu5.0-9B-MLX-4bit | 6.72 GB |
Multimodal architecture
| Component | Architecture | Precision |
|---|---|---|
| Language Backbone | Qwen3.5 hybrid (Gated DeltaNet + full attention, 3:1 ratio) | Quantized (6-bit affine, group_size=64) |
| Vision Encoder | C-RADIOv4-H (ViT-H/16, 653M) | BF16 (full precision) |
| Projector | RMSNorm → Linear(5120→20480) → SquaredReLU → Linear(20480→4096) | BF16 (full precision) |
The vision encoder and multimodal projector are kept at full precision (BF16) to prevent visual reasoning degradation.
Chat template
The MLX conversion embeds the upstream chat template. An external copy is provided as chat_template.jinja for runtimes that require a separate template file.
Usage
Vision understanding with
mlx-vlm
mlx_vlm.generate \
--model abenzerps/ZDTaichu5.0-9B-MLX-6bit \
--image path/to/image.jpg \
--prompt "Describe what is shown in this image in detail." \
--max-tokens 512 \
--temp 0.7
Text generation with
mlx-vlm
mlx_vlm.generate \
--model abenzerps/ZDTaichu5.0-9B-MLX-6bit \
--prompt "Explain why reproducible builds matter." \
--max-tokens 512 \
--temp 0.7
Python API
from mlx_vlm import load, generate
model_id = "abenzerps/ZDTaichu5.0-9B-MLX-6bit"
model, processor = load(model_id)
prompt = "Describe what is shown in this image in detail."
image = "path/to/image.jpg"
output = generate(model, processor, prompt=prompt, image=image, max_tokens=512)
print(output)
Increase context up to 131,072 tokens (128K) when sufficient unified memory is available on Apple Silicon. Tool-call behavior depends on the serving runtime and its parser integration; use the embedded template and verify tool calls in the target application.
Source and build
- Source model: TaichuAI/ZDTaichu5.0-9B
- Source revision: a22afd15a3f85659f103caa659ec4aa9500a998e
- Conversion: ml-explore/mlx / ml-explore/mlx-vlm
- Quantization format: MLX affine quantization (group_size=64, bits=6)
- License: Apache-2.0
Runs of abenzerps ZDTaichu5.0-9B-MLX-6bit on huggingface.co
172
Total runs
-13
24-hour runs
-4
3-day runs
19
7-day runs
177
30-day runs
More Information About ZDTaichu5.0-9B-MLX-6bit huggingface.co Model
Url of ZDTaichu5.0-9B-MLX-6bit
ZDTaichu5.0-9B-MLX-6bit huggingface.co Url
Provider of ZDTaichu5.0-9B-MLX-6bit huggingface.co
Other API from abenzerps
Updated:October 12 2026
Total runs:
2.2M
Run Growth:
2.2M
Growth Rate:
100.00%
Total runs:
507.5K
Run Growth:
290.8K
Growth Rate:
57.64%
Total runs:
344.9K
Run Growth:
272.2K
Growth Rate:
79.45%
Total runs:
182.3K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
10.6K
Run Growth:
-35.8K
Growth Rate:
-319.17%
Total runs:
8.7K
Run Growth:
6.3K
Growth Rate:
73.93%
Total runs:
7.5K
Run Growth:
5.7K
Growth Rate:
88.91%
Total runs:
5.7K
Run Growth:
6.0K
Growth Rate:
86.23%
Total runs:
4.8K
Run Growth:
-292
Growth Rate:
-5.78%
Total runs:
2.6K
Run Growth:
-4.4K
Growth Rate:
-153.64%
Total runs:
1.8K
Run Growth:
-568
Growth Rate:
-28.73%
Total runs:
1.6K
Run Growth:
-4.7K
Growth Rate:
-254.61%
Total runs:
1.6K
Run Growth:
-26
Growth Rate:
-1.58%
Total runs:
1.5K
Run Growth:
-5.5K
Growth Rate:
-326.12%
Total runs:
1.5K
Run Growth:
1.4K
Growth Rate:
100.00%
Total runs:
1.1K
Run Growth:
-432
Growth Rate:
-34.37%
Total runs:
1.1K
Run Growth:
1.1K
Growth Rate:
81.79%
Total runs:
804
Run Growth:
356
Growth Rate:
44.00%
Total runs:
786
Run Growth:
-1.7K
Growth Rate:
-182.49%
Total runs:
666
Run Growth:
-1.9K
Growth Rate:
-268.90%
Total runs:
653
Run Growth:
-386
Growth Rate:
-55.86%
Total runs:
537
Run Growth:
297
Growth Rate:
58.12%
Total runs:
514
Run Growth:
311
Growth Rate:
61.22%
Total runs:
393
Run Growth:
427
Growth Rate:
100.00%
Total runs:
360
Run Growth:
-152
Growth Rate:
-41.76%
Total runs:
326
Run Growth:
-726
Growth Rate:
-214.16%
Total runs:
322
Run Growth:
143
Growth Rate:
50.89%
Total runs:
291
Run Growth:
-135
Growth Rate:
-43.83%
Total runs:
274
Run Growth:
-60
Growth Rate:
-21.43%
Total runs:
254
Run Growth:
-852
Growth Rate:
-326.44%
Total runs:
218
Run Growth:
-333
Growth Rate:
-150.68%
Total runs:
196
Run Growth:
230
Growth Rate:
100.00%
Total runs:
132
Run Growth:
0
Growth Rate:
0.00%
Total runs:
127
Run Growth:
-269
Growth Rate:
-205.34%
Total runs:
10
Run Growth:
3
Growth Rate:
30.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%