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-UNCENSORED-FP8 is an open-weight model for text generation from Waleed, released under MIT License. It has 753.3B parameters. At 16-bit it needs about 1808 GB of GPU memory, which fits on 8x MI325X from $16.00 an hour; at 4-bit, 452 GB on 2x MI325X from $4.00, at the lowest prices in the SAVRN Index.
Parameters753.3B
Context—
Weights—
Licensemit
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve GLM-5.3-UNCENSORED-FP8 (753.3B 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 | 1506.7 GB | 1808.0 GB | 8x MI325X (256 GB) Vultr |
$16.00 | 7x MI355X $18.13 · 7x B300 $46.20 |
| 8-bit | 753.3 GB | 904.0 GB | 4x MI325X (256 GB) Vultr |
$8.00 | 5x MI300X $9.25 · 4x MI355X $10.36 |
| 4-bit | 376.7 GB | 452.0 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.
GLM-5.3-UNCENSORED-FP8 on every accelerator the SAVRN Index prices, at every precision
Model Card
Identity and Version
- Repository
- Whq02/GLM-5.3-UNCENSORED-FP8
- Publisher
- Waleed
- Task
- Text generation
- Modality
- Text
- Library
- Not stated by the source
- Parameters
- 753.3B parameters
- Languages
- en, zh, ru, sr, hi, fr, es, ar
- Revision
- 7da9ef1f1749eed1ade0e86d630c111b501c597d
- First published
- 2026-10-23
- Last updated
- 2026-10-23
License and Download
- License
- mit
- Access
- Open weights, no gate
Download from Waleed
Released by Waleed through its official repository on Hugging Face. Read the license.
Built From
- Derived from zai-org/GLM-5.3
- Quantized from zai-org/GLM-5.3
Memory Requirements
| Precision | Weights in memory |
|---|---|
| 16-bit | 1506.7 GB |
| 8-bit | 753.3 GB |
| 4-bit | 376.7 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About GLM-5.3-UNCENSORED-FP8
How much GPU memory does GLM-5.3-UNCENSORED-FP8 need?
About 1808 GB at 16-bit and 452 GB at 4-bit: the weights (753.3B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run GLM-5.3-UNCENSORED-FP8 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 GLM-5.3-UNCENSORED-FP8 commercially?
Yes. GLM-5.3-UNCENSORED-FP8 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…