Z.ai
GLM-5.3-Flash
A 320B mixture-of-experts model at a sub-2-bit quant, for the longest context on one Spark.
Recommended: DGX Spark, 128 GB unified, $0.79 / hour, billed per minute. Check availability.
Recommended: B300, 288 GB HBM3e, $6.49 / hour, billed per minute. Check availability.
Configure
Every build below is published on Hugging Face and fits at least one GPU we rent. Pick the quantization and engine: the memory it needs, the GPUs it fits and the recommended GPU follow, and Deploy takes that exact build, revision and GPU to the console. Only the one-click preset is tested by GPUwerk.
| Quantization | UD-IQ1_S GGUF |
|---|---|
| Engine | llama.cpp |
| Status | One-click preset |
| Weights | 93.1 GB |
| GPU memory it needs | About 100 GB as the preset serves it |
| Recommended GPU | DGX Spark, $0.79 / hour |
| Weights source | unsloth/GLM-5.3-Flash-GGUF, revision 621d456e93e9, file GLM-5.3-Flash-UD-IQ1_S-00001-of-00003.gguf |
| Licence on the card | mit |
| GPU | Memory | Price | Availability | Deploy |
|---|---|---|---|---|
| RTX 5090x86 · Blackwell | 32 GB GDDR7 | Does not fit: the one-click preset does not run on this GPU. | ||
| DGX SparkArm · GB10 · recommended | 128 GB unified | $0.79 / hour | Check availability | Deploy now GLM-5.3-Flash UD-IQ1_S GGUF on DGX Spark |
| RTX PRO 6000x86 · Blackwell | 96 GB GDDR7 | Does not fit: the one-click preset does not run on this GPU. | ||
| H100 SXMx86 · Hopper | 80 GB HBM3 | Does not fit: the one-click preset does not run on this GPU. | ||
| H200x86 · Hopper | 141 GB HBM3e | Does not fit: the one-click preset does not run on this GPU. | ||
| B200x86 · Blackwell | 180 GB HBM3e | Does not fit: the one-click preset does not run on this GPU. | ||
| B300x86 · Blackwell | 288 GB HBM3e | Does not fit: the one-click preset does not run on this GPU. | ||
| Quantization | NVFP4 |
|---|---|
| Engine | vLLM |
| Status | Untested by GPUwerk |
| Weights | 204.4 GB |
| GPU memory it needs | About 238.1 GB with a 32k-token cache, an estimate |
| Recommended GPU | B300, $6.49 / hour |
| Weights source | nvidia/GLM-5.3-Flash-NVFP4, revision 1d00738646cb |
| Licence on the card | mit |
| GPU | Memory | Price | Availability | Deploy |
|---|---|---|---|---|
| RTX 5090x86 · Blackwell | 32 GB GDDR7 | Does not fit: needs about 238 GB of GPU memory (weights 204.4 GB plus cache, an estimate); RTX 5090 offers 29 GB to it. | ||
| DGX SparkArm · GB10 | 128 GB unified | Does not fit: needs about 238 GB of GPU memory (weights 204.4 GB plus cache, an estimate); DGX Spark offers 96 GB to it. | ||
| RTX PRO 6000x86 · Blackwell | 96 GB GDDR7 | Does not fit: needs about 238 GB of GPU memory (weights 204.4 GB plus cache, an estimate); RTX PRO 6000 offers 86 GB to it. | ||
| H100 SXMx86 · Hopper | 80 GB HBM3 | Does not fit: NVFP4 weights need a Blackwell GPU; H100 is not one. | ||
| H200x86 · Hopper | 141 GB HBM3e | Does not fit: NVFP4 weights need a Blackwell GPU; H200 is not one. | ||
| B200x86 · Blackwell | 180 GB HBM3e | Does not fit: needs about 238 GB of GPU memory (weights 204.4 GB plus cache, an estimate); B200 offers 162 GB to it. | ||
| B300x86 · Blackwell · recommended | 288 GB HBM3e | $6.49 / hour | Check availability | Run it yourself GLM-5.3-Flash NVFP4 on B300 |
Builds by the model's maker, NVIDIA and Unsloth, read from Hugging Face on 21 November 2026. Memory is an estimate (weights x 1.15 plus 3 GB); GGUF runs on llama.cpp, which GPUwerk builds for the DGX Spark only, and NVFP4 needs a Blackwell GPU. SGLang is not offered: there is no SGLang runtime yet.
Details
About the model.
| Maker | Z.ai |
|---|---|
| Task | Text |
| Parameters | 320B total, 18B active (mixture of experts) |
| Context | 262,144 tokens in one slot as served (one-click preset) |
| Licence | See the model card |
No speed figure here: GPUwerk lists only figures it measured itself. Reported figures, with their sources, are in the model guide.
Quick start
- Deploy GLM-5.3-Flash on a DGX Spark. The console opens with the GPU and model picked.
- Wait for the instance to show Running: the model server answers once the weights are loaded.
- Call the HTTPS endpoint from the instance page with an API key, like any OpenAI-compatible API.
curl https://<your-endpoint>/v1/chat/completions \
-H "Authorization: Bearer $GPUWERK_API_KEY" -H "Content-Type: application/json" \
-d '{"model": "glm-5.3-flash", "messages": [{"role": "user", "content": "Hello"}]}'
SSH, the browser terminal, VNC and your workspace work the same on every instance. Terminate when you are done and billing ends.
Related models
Qwen3 Coder 30B
A coding model for agents and editors, with tool calls turned on.
Qwen3.6 35B-A3B
A fast mixture-of-experts model for chat and agents, also on the pay-per-token API.
GPT-OSS 120B
OpenAI's open-weight 120B model, quantized to fit one DGX Spark.