Model reference · open weights

GLM-5.3-Flash

Available as managed deployment LLMs RedHatAI Vision + text 1 variants 10k dl/mo

GLM-5.3-Flash is an open-weight language model from RedHatAI. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

MakerRedHatAI
TypeLanguage models
TaskVision + text
Parameters (lead)169.1B
Runs withtransformers
Based onzai-org/GLM-5.3-Flash
Released2026-08-27
Popularity10k downloads / month
LicenceUnknown

About

What GLM-5.3-Flash is

This model is a quantized version of zai-org/GLM-5.3-Flash.

Model Optimizations

This model was obtained by quantizing the weights of zai-org/GLM-5.3-Flash to NVFP4, ready for inference with vLLM.

Weights are quantized to FP4 with a group size of 16, and activations are quantized to FP4 with local per-group scaling. Only the weights and activations of the linear operators within transformer blocks are quantized using LLM Compressor. Vision tower, embedding, and output head layers are kept in their original precision.

vLLM Serving

docker run --gpus all \
  --privileged --ipc=host -p 8000:8000 \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  -e VLLM_ENGINE_READY_TIMEOUT_S=3600 \
  vllm/vllm-openai:glm53-flash RedHatAI/GLM-5.3-Flash-NVFP4 \
  --tensor-parallel-size 4 \
  --no-enable-flashinfer-autotune \
  --tool-call-parser glm47 \
  --enable-auto-tool-choice \
  --reasoning-parser glm45

Enable Speculative Decoding

docker run --gpus all \
  --privileged --ipc=host -p 8000:8000 \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  -e VLLM_ENGINE_READY_TIMEOUT_S=3600 \
  -e PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True \
  vllm/vllm-openai:glm53-flash RedHatAI/GLM-5.3-Flash-NVFP4 \
  --tensor-parallel-size 4 \
  --no-enable-flashinfer-autotune \
  --tool-call-parser glm47 \
  --enable-auto-tool-choice \
  --reasoning-parser glm45 \
  --gpu-memory-utilization 0.85 \
  --disable-custom-all-reduce \
  --speculative-config '{"method":"mtp","num_speculative_tokens":5}'

Evaluations

BenchmarkMetricAvg Score
GPQA Diamondgpqa_pass@k:k=1 (3 seeds)90.57%
AIME25pass@k:k=1&n=1 (8 seeds)86.67%
GSM8K Platinum CoTexact_match,strict-match (3 seeds)97.74%
MATH-500pass@k:k=1&n=1 (3 seeds)94.87%

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys redhatai-glm-5-3-flash for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (redhatai-glm-5-3-flash below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"redhatai-glm-5-3-flash","messages":[{"role":"user","content":"Hello"}]}'

Create an account — your API key is available in the console. 5M tokens/month currently included with every new account at launch.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms