GLM-5.3-GGUF

How to Run GLM-5.3 Locally

<p style="margin-top: 0; margin-bottom: 0;"> <em>Built from Z.ai's original weights with our own importance matrix. The <a href="https://huggingface.co/datasets/AtomicChat/calib-corpora">calibration corpora</a> behind our builds are public.</em> </p> <div style="display: flex; gap: 8px; align-items: center; margin-top: 10px; margin-bottom: 10px;"> <a href="https://atomic.chat/?utm_source=huggingface&utm_medium=referral&utm_campaign=hf_glm_5_3&utm_content=btn_atomic"><img src="https://huggingface.co/AtomicChat/GLM-5.3-GGUF/resolve/main/btn_atomic.png" width="162" alt="Atomic Chat"></a> <a href="https://discord.gg/8wGSsvmg4V"><img src="https://huggingface.co/AtomicChat/GLM-5.3-GGUF/resolve/main/btn_discord.png" width="119" alt="Discord"></a> <a href="https://github.com/AtomicBot-ai/Atomic-Chat"><img src="https://huggingface.co/AtomicChat/GLM-5.3-GGUF/resolve/main/btn_github.png" width="115" alt="GitHub"></a> </div> <ul style="margin: 0 0 12px 0;"> <li>GLM-5.3 keeps the GLM-5.2 base and takes every gain from post-training. Per Z.ai it is the most capable open-weights model for coding, with open-source SOTA on Terminal Bench 3.0 and Agents' Last Exam.</li> <li>You can now run GLM-5.3 in <a href="https://atomic.chat/?utm_source=huggingface&utm_medium=referral&utm_campaign=hf_glm_5_3&utm_content=bullet_app">Atomic Chat</a> with toggles for Low, High and Max thinking.</li> <li>The quants are still uploading and need a llama.cpp build with GLM-5.3 support; Atomic Chat runs it as support ships.</li> </ul> <hr style="margin: 0 0 16px 0;"> <img src="https://huggingface.co/AtomicChat/GLM-5.3-GGUF/resolve/main/hero.png" alt="Z.ai" style="width:150px; max-width:100%; height:auto;"/>

Highlights

• 753B parameters, read from the published weight index. Mixture-of-Experts: 256 routed experts with 8 active per token plus 1 shared, 78 layers, the first 3 dense.
• Same base as GLM-5.2. Z.ai state every gain comes from post-training, and the two checkpoints carry an identical parameter count.
• Coding: per Z.ai a 50% improvement over GLM-5.2 on their in-house Z.ai Code Bench, and open-source SOTA on Terminal Bench 3.0 and Agents' Last Exam.
• Emergent cyber capability: Z.ai report state of the art on CyberGym for vulnerability discovery, with gains largest further up the exploitation chain, more than doubling GLM-5.2 on exploitation benchmarks.
• Thinking budget controlled by reasoning_effort with three levels, low, high and max. It defaults to max.
• Sparse attention with a learned indexer (glm_moe_dsa, top-2048 index), and one multi-token-prediction block in the checkpoint.
• Bilingual, English and Chinese.
• Ships in FP8 upstream, so our GGUF base is converted from the FP8 checkpoint rather than from BF16.
• Full imatrix quantization with our public calibration corpora.

[!NOTE] These GGUFs are self-quantized from the original weights, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.

[!IMPORTANT] This is a 753B model. Even at four bits a full set of weights runs to several hundred gigabytes, and all of it has to fit in fast memory. In practice that means a large-RAM server or a serious multi-GPU rig, not a laptop and not most workstations.

[!IMPORTANT] Always pass --jinja so the GLM-5.3 chat template is applied. Z.ai note that clear_thinking defaults to false in that template, so pass clear_thinking=true for chat scenarios.

Model Overview

<img src="https://huggingface.co/AtomicChat/GLM-5.3-GGUF/resolve/main/benchmark.png" alt="GLM-5.3 benchmark scores" style="width:100%; max-width:900px;"/>

Scores are Z.ai's published results for the base zai-org/GLM-5.3. Selected numbers from their table: Terminal Bench 2.1 88.2, Terminal Bench 3.0 28.3, DeepSWE 1.1 66.9, CyberGym 84.5, AutomationBench 48.2, HLE w/ tools 62.5, GDPval-AA v2 1769.

Choosing a quant

[!TIP] Sizes fill in once the quants finish uploading. Pick the largest file that fits your memory with room for context.

AD- marks an Atomic Dynamic layout: bits are assigned per tensor role rather than left to a preset, with the router and the shared expert held high and the routed experts carrying the compression.

Get started

[!NOTE] GLM-5.3 uses the glm_moe_dsa architecture. The quants in this repo are still uploading, and running them needs a llama.cpp build that has landed GLM-5.3 support. Until then, Atomic Chat is the easiest way to run it as support ships.

Run GLM-5.3 locally with:

• Atomic Chat: the easiest path. Open the app, search AtomicChat/GLM-5.3-GGUF, pick a quant, hit Use this model.
• llama.cpp: llama-server -hf AtomicChat/GLM-5.3-GGUF:AD-Q4_K_M --jinja -c 8192
• Ollama: ollama run hf.co/AtomicChat/GLM-5.3-GGUF:AD-Q4_K_M
• LM Studio / Jan: search the repo id, download any quant.

For the original FP8 weights rather than GGUF, Z.ai list SGLang, vLLM, TokenSpeed, Transformers and KTransformers on the base model card.

Best practices

From Z.ai's evaluation settings (HLE w/ tools). Per-benchmark settings vary; see the base model card for details.

Run in llama.cpp

git clone https://github.com/ggml-org/llama.cpp
cmake llama.cpp -B llama.cpp/build -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
cmake --build llama.cpp/build --config Release -j --target llama-cli llama-server

./llama.cpp/build/bin/llama-server \
    -hf AtomicChat/GLM-5.3-GGUF:AD-Q4_K_M \
    --jinja -ngl 99 -c 8192 -fa on

How these were made

1. Download zai-org/GLM-5.3 (original FP8 weights).
2. Convert to GGUF with a llama.cpp build that supports the GLM-5.3 architecture (glm_moe_dsa, sparse attention with a learned indexer).
3. Build an importance matrix over our public calibration corpora.
4. Quantize the ladder with --imatrix, assigning bits per tensor role: router and shared expert high, routed experts carrying the compression.

License

Released by Z.ai (zai-org) under the GLM-5.3 license. Quantized by Atomic Chat.