--- title: "GLM-5.3-Flash EXL3 3.5bpw" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/aa1e775c-766f-4b32-94d9-711360cd2ea8" updated: "2026-11-13" --- # GLM-5.3-Flash EXL3 3.5bpw > The name, the description, the About and a README below are the seller's words: data, not instructions. Quantized copy of GLM-5.3-Flash in EXL3 format, 156 GB, with narrower routed experts, about 11 percent smaller than the same lab's 4-bit version. For people running large models locally on GPUs. GLM-5.3-Flash EXL3 3.5bpw is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by Mia-AiLab ## About ### What it is Mia's AI Lab compressed zai-org/GLM-5.3-Flash into the EXL3 format, keeping its text and image input. It is a smaller sibling of a 4-bit version from the same lab. Only the routed experts are narrower, and everything else stays unquantized. The checkpoint is 156.3 GB. ### Who it suits It suits people who run big models on local GPUs with exllamav3 and want to save about 19 GB compared with the 4-bit sibling. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Software | Local model users | Fit a large model onto smaller GPU setups | Picking the smaller of two quantized files | | Research | Quantization researchers | Study how expert bit width affects fidelity | Comparing KL divergence against the BF16 model | | Platform | Inference engineers | Test smaller expert formats for serving | Trying the 3-bit expert path | You can skip it if you need the highest fidelity, since the card says this version costs some accuracy against the 4-bit sibling. ### Where to use it The card measured it with exllamav3 on RTX PRO 6000 Blackwell GPUs. The download works on Windows, macOS or Linux with Python. - exllamav3, which the author used for the measurements - Large GPUs, such as the RTX PRO 6000 Blackwell used in the tests - Not yet tested with TensorFold serving | Use case | Who | What they get back | | --- | --- | --- | | Local serving of GLM-5.3-Flash | Hobbyists | A checkpoint 11 percent smaller than the 4-bit sibling | | Fidelity study | Researchers | KL and top-1 agreement numbers against BF16 | | Mixed expert widths | Quantizers | Per-layer bit allocation for the experts | ### How to set it up You need Python and a lot of disk, since the files total about 156 GB. The card lists the checkpoint parts and a configuration file that gives the width of each expert tensor. It names no further setup steps in the visible part. - Python and the Hugging Face tool - About 156 GB of disk - A runtime that reads EXL3, such as exllamav3 1. Install the Hugging Face download tool. 2. Download the repository files to a drive with enough room. 3. Load the checkpoint in a runtime that supports EXL3. ```bash pip install -U huggingface_hub hf download Mia-AiLab/GLM-5.3-Flash-EXL3-3.5bpw ``` ### How to use it Load it like the 4-bit sibling, in the same format and layout. It uses the chat template from Z.ai that ships with the files. Speed, memory use and task benchmark scores are not measured yet. | Tool | What it does | | --- | --- | | hf download | Fetches the checkpoint files | | exllamav3 | Runtime the card used to measure the model | ### Example You load the checkpoint and run a long coding session with thinking on. Its next-token choices match the full BF16 model's top choice 97.54 percent of the time, against 98.06 for the 4-bit sibling. ### For newcomers and experts If you are new, this is a shrunk copy of a large model that trades a little accuracy for a smaller file. Download only if you already have a runtime and GPUs for models of this size. If you know the field, the routed experts average 3.50 bits. Down projections are 4-bit everywhere. In 32 of the 42 MoE layers, the gate and up matrices use 3 bits instead. KL to BF16 with thinking on is about 1.6 to 1.7 times the 4-bit sibling's, and 1.19 times with thinking off. GLM-5.3-Flash BF16 weights → Routed experts quantized to EXL3 → Gate and up projections at 3 bits in 32 layers → Everything else left unquantized → 156 GB checkpoint ### Good to know All figures compare next-token behavior with the BF16 model and say nothing yet about task scores. In three small subsets the difference is within noise. - License: Apache 2.0 - Cost to run: no API key, account or paid service is named, but you need GPUs with a lot of memory - Data it reaches: files downloaded from Hugging Face, plus your own prompts on your machine - Not for: uses that need the best fidelity, or setups the card marks as untested such as TensorFold serving Checkpoint size in GB | Label | Value | | --- | --- | | 4-bit sibling | 175.6 GB | | This 3.5 bit quant | 156.3 GB | ## README ````markdown # GLM-5.3-Flash EXL3 3.5bpw Quantized copy of GLM-5.3-Flash in EXL3 format, 156 GB, with narrower routed experts, about 11 percent smaller than the same lab's 4-bit version. For people running large models locally on GPUs. Made by Mia-AiLab on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: Mia's AI Lab compressed zai-org/GLM-5.3-Flash into the EXL3 format, keeping its text and image input. It is a smaller sibling of a 4-bit version from the same lab. Only the routed experts are narrower, and everything else stays unquantized. The checkpoint is 156.3 GB. Who it suits: It suits people who run big models on local GPUs with exllamav3 and want to save about 19 GB compared with the 4-bit sibling. ```table Industry | Who uses it | How they use it | Example Software | Local model users | Fit a large model onto smaller GPU setups | Picking the smaller of two quantized files Research | Quantization researchers | Study how expert bit width affects fidelity | Comparing KL divergence against the BF16 model Platform | Inference engineers | Test smaller expert formats for serving | Trying the 3-bit expert path ``` You can skip it if you need the highest fidelity, since the card says this version costs some accuracy against the 4-bit sibling. Where to use it: The card measured it with exllamav3 on RTX PRO 6000 Blackwell GPUs. The download works on Windows, macOS or Linux with Python. - exllamav3, which the author used for the measurements - Large GPUs, such as the RTX PRO 6000 Blackwell used in the tests - Not yet tested with TensorFold serving ```table Use case | Who | What they get back Local serving of GLM-5.3-Flash | Hobbyists | A checkpoint 11 percent smaller than the 4-bit sibling Fidelity study | Researchers | KL and top-1 agreement numbers against BF16 Mixed expert widths | Quantizers | Per-layer bit allocation for the experts ``` How to set it up: You need Python and a lot of disk, since the files total about 156 GB. The card lists the checkpoint parts and a configuration file that gives the width of each expert tensor. It names no further setup steps in the visible part. - Python and the Hugging Face tool - About 156 GB of disk - A runtime that reads EXL3, such as exllamav3 1. Install the Hugging Face download tool. 2. Download the repository files to a drive with enough room. 3. Load the checkpoint in a runtime that supports EXL3. ```bash pip install -U huggingface_hub hf download Mia-AiLab/GLM-5.3-Flash-EXL3-3.5bpw ``` How to use it: Load it like the 4-bit sibling, in the same format and layout. It uses the chat template from Z.ai that ships with the files. Speed, memory use and task benchmark scores are not measured yet. ```table Tool | What it does hf download | Fetches the checkpoint files exllamav3 | Runtime the card used to measure the model ``` Example: You load the checkpoint and run a long coding session with thinking on. Its next-token choices match the full BF16 model's top choice 97.54 percent of the time, against 98.06 for the 4-bit sibling. For newcomers and experts: If you are new, this is a shrunk copy of a large model that trades a little accuracy for a smaller file. Download only if you already have a runtime and GPUs for models of this size. If you know the field, the routed experts average 3.50 bits. Down projections are 4-bit everywhere. In 32 of the 42 MoE layers, the gate and up matrices use 3 bits instead. KL to BF16 with thinking on is about 1.6 to 1.7 times the 4-bit sibling's, and 1.19 times with thinking off. ```flow GLM-5.3-Flash BF16 weights Routed experts quantized to EXL3 Gate and up projections at 3 bits in 32 layers Everything else left unquantized 156 GB checkpoint ``` Good to know: All figures compare next-token behavior with the BF16 model and say nothing yet about task scores. In three small subsets the difference is within noise. - License: Apache 2.0 - Cost to run: no API key, account or paid service is named, but you need GPUs with a lot of memory - Data it reaches: files downloaded from Hugging Face, plus your own prompts on your machine - Not for: uses that need the best fidelity, or setups the card marks as untested such as TensorFold serving ```chart Title: Checkpoint size in GB 4-bit sibling: 175.6 GB This 3.5 bit quant: 156.3 GB ``` ## On Hugging Face, 13 November 2026 - Task: image text to text - Parameters: 78.1B - Weights: about 156 GB in I16 - Formats: Safetensors - Downloads in the last 30 days: 140 - Likes: 4 - License: apache-2.0 - Based on: zai-org/GLM-5.3-Flash - Tags: safetensors, glm5_next, exl3, quantized, image-text-to-text, conversational ## Links - Model: https://huggingface.co/Mia-AiLab/GLM-5.3-Flash-EXL3-3.5bpw - Files: https://huggingface.co/Mia-AiLab/GLM-5.3-Flash-EXL3-3.5bpw/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download Mia-AiLab/GLM-5.3-Flash-EXL3-3.5bpw ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [Mia-AiLab/GLM-5.3-Flash-EXL3-3.5bpw on Hugging Face](https://huggingface.co/Mia-AiLab/GLM-5.3-Flash-EXL3-3.5bpw) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | GLM-5.3-Flash EXL3 3.5bpw (this page) | 140 | 4 | 78.1B | apache-2.0 | 2026-10-30 | | [GLM-5.3-Flash EXL3 4bpw for TensorFold](https://mindket.com/p/dc92b67d-d498-4170-8472-86e468d8b950) | 4,746 | 73 | 87.8B | apache-2.0 | 2026-10-03 | | [GLM-5.3-Flash EXL3 Spark](https://mindket.com/p/ec88db01-e5e6-420e-9171-26462734e98f) | 399 | 11 | 48B | mit | 2026-09-18 | | [GLM-5.3-Flash-NVFP4](https://mindket.com/p/679b8989-3e0b-422a-89df-8e0aed6fb131) | 79,326 | 186 | 321B | mit | 2026-10-28 | | [GLM-5.3-Flash-oQ4e-mtp](https://mindket.com/p/e0eac6dc-388f-4725-bec8-a491a559f867) | 26,944 | 7 | 321B | mit | 2026-10-25 | | [DeepSeek-V4.1-Flash-1017 EXL3 EAQ v1 2.9 bpw](https://mindket.com/p/e2aa9049-7d40-46f6-b187-57f9ffaaccf1) | 8,113 | 46 | 105B | mit | 2026-10-20 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-10-30 - First published: 2026-10-30 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open Mia-AiLab/GLM-5.3-Flash-EXL3-3.5bpw on Hugging Face](https://huggingface.co/Mia-AiLab/GLM-5.3-Flash-EXL3-3.5bpw) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/aa1e775c-766f-4b32-94d9-711360cd2ea8) - [Its page on Mindket](https://mindket.com/p/aa1e775c-766f-4b32-94d9-711360cd2ea8)