GLM-5.3 uses the same base model as GLM-5.2 — every gain comes from post-training. Compared with GLM-5.2, it is much better at complex coding and long-horizon tasks: GLM-5.3 supports deployment with the following frameworks. Feel free to try them out: - SGLang — see cookbook - vLLM — see recipes - TokenSpeed — see here - Transformers — see transformers docs - KTransformers — see tutorial - Unsloth — see guide - For deployment on the Ascend NPU platform, inference frameworks such as vLLM-Ascend, xLLM and SGLang are supported — see here. - GLM-5.3 supports controlling the thinking budget through the reasoningeffort parameter, which accepts three levels: low, high, and max. It defaults to max…
Open-weight model · Text generation
DeepSeek-V4.1-Flash-1017-MXFP4-uncensored
by Angle Death Lordking998/DeepSeek-V4.1-Flash-1017-MXFP4-uncensored
DeepSeek-V4.1-Flash-1017-MXFP4-uncensored is an open-weight model for text generation from Angle Death, released under MIT License. It has 763.2B parameters. At 16-bit it needs about 1831.7 GB of GPU memory, which fits on 8x MI325X from $16.00 an hour; at 4-bit, 457.9 GB on 2x MI325X from $4.00, at the lowest prices in the SAVRN Index.
Parameters763.2B
Context—
Weights—
Licensemit
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve DeepSeek-V4.1-Flash-1017-MXFP4-uncensored (763.2B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 1526.4 GB | 1831.7 GB | 8x MI325X (256 GB) Vultr |
$16.00 | 7x MI355X $18.13 · 7x B300 $46.20 |
| 8-bit | 763.2 GB | 915.8 GB | 4x MI325X (256 GB) Vultr |
$8.00 | 5x MI300X $9.25 · 4x MI355X $10.36 |
| 4-bit | 381.6 GB | 457.9 GB | 2x MI325X (256 GB) Vultr |
$4.00 | 2x MI355X $5.18 · 3x MI300X $5.55 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 23, 2026.
Model Card
Identity and Version
- Repository
- Lordking998/DeepSeek-V4.1-Flash-1017-MXFP4-uncensored
- Publisher
- Angle Death
- Task
- Text generation
- Modality
- Text
- Library
- vllm
- Parameters
- 763.2B parameters
- Languages
- Not stated by the source
- Revision
- 065edc711f1415001e007e6ae18c2894ab32baec
- First published
- 2026-10-22
- Last updated
- 2026-10-22
License and Download
- License
- mit
- Access
- Open weights, no gate
Download from Angle Death
Released by Angle Death through its official repository on Hugging Face. Read the license.
Built From
- Derived from deepseek-ai/DeepSeek-V4.1-Flash-1017
- Quantized from deepseek-ai/DeepSeek-V4.1-Flash-1017
Memory Requirements
| Precision | Weights in memory |
|---|---|
| 16-bit | 1526.4 GB |
| 8-bit | 763.2 GB |
| 4-bit | 381.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About DeepSeek-V4.1-Flash-1017-MXFP4-uncensored
How much GPU memory does DeepSeek-V4.1-Flash-1017-MXFP4-uncensored need?
About 1831.7 GB at 16-bit and 457.9 GB at 4-bit: the weights (763.2B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run DeepSeek-V4.1-Flash-1017-MXFP4-uncensored on?
At 16-bit, 8x MI325X from $16.00 an hour; at 4-bit, 2x MI325X from $4.00 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use DeepSeek-V4.1-Flash-1017-MXFP4-uncensored commercially?
Yes. DeepSeek-V4.1-Flash-1017-MXFP4-uncensored is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.
Similar Models
Join our WeChat or Discord community. Check out the GLM-5.2 blog and GLM-5 Technical report. Use GLM-5.2 API services on Z.ai API Platform. Try GLM-5.2 here. [ Paper ] [ GitHub ] We're introducing GLM-5.2, our latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a solid 1M-token context. GLM-5.2's new capabilities include: GLM-5.2 supports deployment with the following frameworks. Feel free to try them out: - SGLang (v0.5.13.post1+) — see cookbook - vLLM (v0.23.0+) — see recipes - Transformers (v0.5.12+) — see transformers docs - KTransformers (v0.5.12+)…
Join our WeChat or Discord community. Check out the GLM-5.2 blog and GLM-5 Technical report. Use GLM-5.2 API services on Z.ai API Platform. Try GLM-5.2 here. [ Paper ] [ GitHub ] We're introducing GLM-5.2, our latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a solid 1M-token context. GLM-5.2's new capabilities include: GLM-5.2 supports deployment with the following frameworks. Feel free to try them out: - SGLang (v0.5.13.post1+) — see cookbook - vLLM (v0.23.0+) — see recipes - Transformers (v0.5.12+) — see transformers docs - KTransformers (v0.5.12+)…
GLM-5.3 uses the same base model as GLM-5.2 — every gain comes from post-training. Compared with GLM-5.2, it is much better at complex coding and long-horizon tasks: GLM-5.3 supports deployment with the following frameworks. Feel free to try them out: - SGLang — see cookbook - vLLM — see recipes - TokenSpeed — see here - Transformers — see transformers docs - KTransformers — see tutorial - Unsloth — see guide - For deployment on the Ascend NPU platform, inference frameworks such as vLLM-Ascend, xLLM and SGLang are supported — see here. - GLM-5.3 supports controlling the thinking budget through the reasoningeffort parameter, which accepts three levels: low, high, and max. It defaults to max…
GLM-5.3 uses the same base model as GLM-5.2 — every gain comes from post-training. Compared with GLM-5.2, it is much better at complex coding and long-horizon tasks: GLM-5.3 supports deployment with the following frameworks. Feel free to try them out: - SGLang — see cookbook - vLLM — see recipes - TokenSpeed — see here - Transformers — see transformers docs - KTransformers — see tutorial - Unsloth — see guide - For deployment on the Ascend NPU platform, inference frameworks such as vLLM-Ascend, xLLM and SGLang are supported — see here. - GLM-5.3 supports controlling the thinking budget through the reasoningeffort parameter, which accepts three levels: low, high, and max. It defaults to max…
GLM-5.3 uses the same base model as GLM-5.2 — every gain comes from post-training. Compared with GLM-5.2, it is much better at complex coding and long-horizon tasks: GLM-5.3 supports deployment with the following frameworks. Feel free to try them out: - SGLang — see cookbook - vLLM — see recipes - TokenSpeed — see here - Transformers — see transformers docs - KTransformers — see tutorial - Unsloth — see guide - For deployment on the Ascend NPU platform, inference frameworks such as vLLM-Ascend, xLLM and SGLang are supported — see here. - GLM-5.3 supports controlling the thinking budget through the reasoningeffort parameter, which accepts three levels: low, high, and max. It defaults to max…