| --- |
| license: mit |
| license_link: https://huggingface.co/zai-org/GLM-5.3-Flash/blob/main/LICENSE |
| base_model: |
| - zai-org/GLM-5.3-Flash |
| base_model_relation: quantized |
| quantized_by: AtomicChat |
| language: |
| - en |
| - zh |
| pipeline_tag: text-generation |
| library_name: gguf |
| tags: |
| - atomic-chat |
| - glm |
| - glm-5 |
| - zai-org |
| - moe |
| - multimodal |
| - gguf |
| - imatrix |
| - quantized |
| - llama.cpp |
| --- |
| |
| # How to Run GLM-5.3-Flash 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_flash&utm_content=btn_atomic"><img src="https://huggingface.co/AtomicChat/GLM-5.3-Flash-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-Flash-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-Flash-GGUF/resolve/main/btn_github.png" width="115" alt="GitHub"></a> |
| </div> |
| <ul style="margin: 0 0 12px 0;"> |
| <li>GLM-5.3-Flash is the first natively multimodal model in the GLM-5 series (320B total, 18B active).</li> |
| <li>These GGUFs are self-quantized from Z.ai's original weights with our own importance matrix, published alongside the quants.</li> |
| <li>The quants are still uploading and need a llama.cpp build with GLM-5.3-Flash 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-Flash-GGUF/resolve/main/hero.png" alt="Z.ai" style="width:150px; max-width:100%; height:auto;"/> |
|
|
| ## Highlights |
|
|
| - **320B total / 18B active** Mixture-of-Experts. The first natively multimodal model in the GLM-5 series; per Z.ai it outperforms GLM-5.2 across benchmarks at about one-tenth the price, and approaches Claude Opus 4.8 on coding and agentic tasks. |
| - **Hybrid attention**: combines sparse and linear attention to sharply cut long-context serving cost while preserving precise long-context capability. A first for the GLM series. |
| - **Manifold-Constrained Hyper-Connections (mHC)** to further improve scaling efficiency. |
| - **Newly trained base** on a 30T-token multimodal pre-training corpus. |
| - **Bilingual**, English and Chinese. |
| - **Natively multimodal** (text and vision). These GGUF quants cover the text path. |
| - **Frontier coding and agentic scores** (Z.ai-reported): Terminal-Bench 2.1 84.3, DeepSWE 1.1 63.4, HLE w/ tools 55.3, AutomationBench 48.8. |
| - **Full imatrix quantization** with our public [calibration corpora](https://huggingface.co/datasets/AtomicChat/calib-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] |
| > Always pass `--jinja` so the **GLM-5.3-Flash chat template** is applied. Without it the model can emit malformed turns. |
|
|
| ## Model Overview |
|
|
| | Property | Value | |
| |---|---| |
| | Base model | `zai-org/GLM-5.3-Flash` | |
| | Total / active parameters | 320B total / 18B active | |
| | Architecture | Hybrid sparse + linear attention MoE with Manifold-Constrained Hyper-Connections (mHC) | |
| | Modality | Natively multimodal (text and vision); this repo covers the text path | |
| | Languages | English, Chinese | |
| | Pre-training | 30T-token multimodal corpus | |
| | Context length | Not stated by Z.ai; evaluations run up to 1,000,000 tokens with context management | |
| | This repo | GGUF quants (imatrix), text path. The importance matrix we built is published here too. | |
|
|
| <img src="https://huggingface.co/AtomicChat/GLM-5.3-Flash-GGUF/resolve/main/benchmark.png" alt="GLM-5.3-Flash benchmark scores" style="width:100%; max-width:900px;"/> |
|
|
| Scores are Z.ai's published results for the base `zai-org/GLM-5.3-Flash`. Quantization preserves the large majority of this; `Q4_K_M` and up sit within a point or two of full precision. |
|
|
|
|
| ## Choosing a quant |
|
|
| | Quant | Size | Notes | |
| |---|---|---| |
| | `IQ2_M` | — | Smallest usable. Aggressive low-bit for memory-constrained boxes. | |
| | `IQ3_M` | — | Beats Q3 at similar size thanks to imatrix. Best low-RAM pick. | |
| | **`Q4_K_M`** | — | **Recommended default. Best balance of size, speed and quality.** | |
| | **`UD-Q4_K_XL`** | — | **Dynamic. Embeddings and output kept at Q8_0 for higher quality at a Q4 footprint.** | |
| | `Q6_K` | — | Near lossless. | |
| | `Q8_0` | — | Effectively lossless, reference quality. | |
| |
| > [!TIP] |
| > Sizes fill in once the quants finish uploading. Pick the largest file that fits your (V)RAM with room for context. |
| |
| ## Get started |
| |
| > [!NOTE] |
| > GLM-5.3-Flash uses a new hybrid sparse + linear attention architecture with Manifold-Constrained Hyper-Connections. The quants in this repo are still uploading, and running them needs a `llama.cpp` build that has landed GLM-5.3-Flash support. Until then, [Atomic Chat](https://atomic.chat) is the easiest way to run it as support ships. |
| |
| Run GLM-5.3-Flash locally with: |
| |
| - **[Atomic Chat](https://atomic.chat):** the easiest path. Open the app, search `AtomicChat/GLM-5.3-Flash-GGUF`, pick a quant, hit **Use this model**. |
| - **llama.cpp:** `llama-server -hf AtomicChat/GLM-5.3-Flash-GGUF:Q4_K_M --jinja -c 8192` |
| - **Ollama:** `ollama run hf.co/AtomicChat/GLM-5.3-Flash-GGUF:Q4_K_M` |
| - **LM Studio / Jan:** search the repo id, download any quant. |
| |
| ## Best practices |
| |
| | Parameter | Value | |
| |---|---| |
| | temperature | 1.0 | |
| | top_p | 0.95 | |
| |
| From Z.ai's evaluation settings (HLE w/ tools). Per-benchmark settings vary; see the base model card for details. |
| |
| ## Run in llama.cpp |
| |
| ```bash |
| git clone https://github.com/ggerganov/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 |
| ``` |
| |
| ```bash |
| ./llama.cpp/build/bin/llama-server \ |
| -hf AtomicChat/GLM-5.3-Flash-GGUF:UD-Q4_K_XL \ |
| --jinja -ngl 99 -c 8192 -fa on |
| ``` |
| |
| ## How these were made |
| |
| 1. Download `zai-org/GLM-5.3-Flash` (original weights). |
| 2. Convert to GGUF with a [llama.cpp](https://github.com/ggerganov/llama.cpp) build that supports the GLM-5.3-Flash architecture (hybrid sparse + linear attention, mHC). |
| 3. Build an importance matrix over our public [calibration corpora](https://huggingface.co/datasets/AtomicChat/calib-corpora). |
| 4. Quantize the ladder with `--imatrix`; `UD-Q4_K_XL` additionally pins the token-embedding and output tensors to `Q8_0`. |
| |
| ## License |
| |
| Released by Z.ai (zai-org) under the MIT license. Quantized by Atomic Chat. |
| |
| |
