---
title: DeepSeek-V4.1-Flash-1017-oQ2e-mtp
canonical_url: "https://www.modelscope.cn/models/mlx-community/DeepSeek-V4.1-Flash-1017-oQ2e-mtp"
md_url: "https://www.modelscope.cn/models/mlx-community/DeepSeek-V4.1-Flash-1017-oQ2e-mtp.md"
repository: mlx-community/DeepSeek-V4.1-Flash-1017-oQ2e-mtp
last_updated: 2026-10-17
license: mit
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - deepseek_v41
architectures:
  - DeepseekV41ForCausalLM
base_model:
  - deepseek-ai/DeepSeek-V4.1-Flash-1017
base_model_relation: quantized
parameters: 36.9B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 188
stars: 0
tags:
  - mlx
  - oq
  - quantized
  - deepseek_v41
  - mtp
---

# DeepSeek-V4.1-Flash-1017-oQ2e-mtp

> DeepSeek-V4.1-Flash-1017-oQ2e-mtp - mlx-community 在 ModelScope 开源的模型。DeepSeek-V4.1-Flash-1017-oQ2e-mtp

mlx-community/DeepSeek-V4.1-Flash-1017-oQ2e-mtp 是 ModelScope 魔搭社区上的 36.9B 参数image-text-to-text模型，采用 mit 许可，基于 deepseek-ai/DeepSeek-V4.1-Flash-1017 构建。

- **Repository**: mlx-community/DeepSeek-V4.1-Flash-1017-oQ2e-mtp
- **License**: mit
- **Tasks**: image-text-to-text
- **Parameters**: 36.9B
- **Base model**: deepseek-ai/DeepSeek-V4.1-Flash-1017
- **Tags**: mlx, oq, quantized, deepseek_v41, mtp
- **Downloads**: 188
- **Stars**: 0
- **Last updated**: 2026-10-17

Source: https://www.modelscope.cn/models/mlx-community/DeepSeek-V4.1-Flash-1017-oQ2e-mtp

---

# DeepSeek-V4.1-Flash-1017-oQ2e-mtp

This model was quantized using [oQ](https://github.com/jundot/omlx) (oMLX v0.7.1) mixed-precision quantization with Improved oQe Quantization ([jundot/omlx#4385](https://github.com/jundot/omlx/pull/4385)).

A mixed-precision MLX checkpoint of [deepseek-ai/DeepSeek-V4.1-Flash-1017](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017), a minor update to [DeepSeek-V4.1-Flash](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash) with improved reasoning, coding, agentic and visual performance. It is a multimodal mixture-of-experts model with 552B backbone parameters, a Causal Encoder-Decoder layout, Compressed Sparse Attention 2 (CSA2), Engram conditional memory and DSpark speculative decoding. It includes the language model, the Engram tables, the vision encoder, the multimodal aligner and the DSpark MTP weights.

The effective average is 2.688 bits/weight excluding the Engram tables, or 3.284 bits/weight for the complete checkpoint.

## Quantization and Bit Distribution

oQ2e allocates bits by measured layer sensitivity, then rounds each group with an importance matrix (1024 samples x 512 tokens) and a weighted least-squares refit of its scale and bias. Below oQ4, the Engram tables stay at 4 bits and are left out of the bit budget, because oMLX can serve them from SSD instead of memory.

| Storage format | Logical weights | Share of total | Tensor storage | Effective bits/weight |
|---|---|---|---|---|
| Affine 2-bit, group 64 | 543.582B | 71.224% | 158.203 GiB | 2.50 |
| MXFP4, group 32 | 13.590B | 1.781% | 6.724 GiB | 4.25 |
| Affine 8-bit, group 64 | 5.200B | 0.681% | 5.145 GiB | 8.50 |
| MXFP8, group 32 | 0.779B | 0.102% | 0.748 GiB | 8.25 |
| BF16 | 3.399B | 0.445% | 6.332 GiB | 16.00 |
| FP32 | 0.042B | 0.006% | 0.158 GiB | 32.00 |
| Engram affine 4-bit, group 32 | 196.614B | 25.762% | 114.444 GiB | 5.00 |
| **Total** | **763.205B** | **100%** | **291.754 GiB** | **3.284** |

## Storage Breakdown

| Component | Logical weights | Storage |
|---|---|---|
| Language backbone | 551.881B | 181.366 GB / 168.911 GiB |
| Engram tables | 196.614B | 122.884 GB / 114.444 GiB |
| Vision encoder | 0.485B | 0.971 GB / 0.904 GiB |
| MTP head | 14.225B | 8.047 GB / 7.495 GiB |
| **Total** | **763.205B** | **313.268 GB / 291.754 GiB** |

## License

MIT, following the source model. See `LICENSE`.