DeepSeek V4 Flash MLX 9bit EXP
Fonte do modelo
- Tipo
- Other
- Tamanho do arquivo
- 9,02–10,00 GB
- Atualizado
- 26 de set. de 2026
- Publicador
- @inferencerlabs
- Tarefas
- Geração de texto
Trecho da fonte
Artefatos de modelo
15 artefatos
Artefatos de modelo
15 artefatosmodel-00001-of-00015.safetensors
safetensors · 9,49 GB · SHA-256 47f0ea5a2932…e43b
model-00002-of-00015.safetensors
safetensors · 9,96 GB · SHA-256 ebbeb0d3a7f9…890a
model-00003-of-00015.safetensors
safetensors · 9,04 GB · SHA-256 540391b2703d…aa9f
model-00004-of-00015.safetensors
safetensors · 9,96 GB · SHA-256 6f8ea1a75c4e…49fc
model-00005-of-00015.safetensors
safetensors · 9,04 GB · SHA-256 7d74bb94300b…a184
model-00006-of-00015.safetensors
safetensors · 9,98 GB · SHA-256 5cb1aba8ab52…ae58
model-00007-of-00015.safetensors
safetensors · 9,99 GB · SHA-256 e455906eab5d…4788
model-00008-of-00015.safetensors
safetensors · 10,00 GB · SHA-256 a5fcfb013087…06ae
model-00009-of-00015.safetensors
safetensors · 10,00 GB · SHA-256 acbafdc1a279…8daa
model-00010-of-00015.safetensors
safetensors · 9,97 GB · SHA-256 8542c5f9414d…74b4
model-00011-of-00015.safetensors
safetensors · 9,02 GB · SHA-256 f4d7fe8ac78d…d80d
model-00012-of-00015.safetensors
safetensors · 9,97 GB · SHA-256 f9bf4164aa49…7c56
model-00013-of-00015.safetensors
safetensors · 9,02 GB · SHA-256 ae080c80d08c…dc8e
model-00014-of-00015.safetensors
safetensors · 9,97 GB · SHA-256 0d747c1cf332…7155
model-00015-of-00015.safetensors
safetensors · 9,46 GB · SHA-256 34bcfb2d41e4…67c8
Trechos de fonte
3 trechos
Trechos de fonte
3 trechos--- language: en tags: - quantized - mlx base_model: - deepseek-ai/DeepSeek-V4-Flash base_model_relation: quantized library_name: mlx pipeline_tag: text-generation --- # DeepSeek-V4-Flash See DeepSeek-V4-Flash in action: [demonstration videos](https://youtube.com/xcreate) For improved performance, download and enable a compatible [MTP speculative decoder](https://huggingface.co/models?search=inferencerlabs/deepseek-v4-flash-mtp-mlx). #### Tested on an M3 Ultra 512 GiB RAM using [Inferencer app v1.11.7](https://inferencer.com) <table style="border-collapse: collapse; border: none; text-align:left; margin-top:10px; margin-bottom:0px;"> <tr><td><strong>Text inference</strong></td><td>~31 tokens/s @ 1000 tokens ~148.5 GiB</td></tr> <tr><td><strong>Text inference (with MTP)</strong></td><td>~37.3 tokens/s @ 1000 tokens ~152.9 GiB</td></tr> </table> <p style="margin-bottom:0px;"> <strong>Q9 typically achieves near lossless accuracy in our coding test</strong> In this build, the 4-bit pre-quantized weights of the base model were repacked (rather than dequantized and re-quantized to 9-bit), as this approach performed slightly better in our initial coding tests. All remaining weights were quantized to 9-bit. </p>  ##### Quantized with a modified version of [MLX](https://github.com/ml-explore/mlx) ##### For more details see our [demonstration videos](https://youtube.com/xcreate) or visit [DeepSeek-V4-Flash](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash). ## Disclaimer We are not the creator, originator, or owner of any model listed. Each model is created and provided by third parties. Models may not always be accurate or contextually appropriate. You are responsible for verifying the information before making important decisions. We are not liable for any damages, losses, or issues arising from its use, including data loss or inaccuracies in AI-generated content.
Source context: 1574 downloads · 4 likes · Pipeline text-generation · Library mlx · Repo inferencerlabs/DeepSeek-V4-Flash-MLX-Q9
Source context: 1706 downloads · 4 likes · Pipeline text-generation · Library mlx · Repo inferencerlabs/DeepSeek-V4-Flash-MLX-Q9
