Dedicated model · Available as managed deployment
Z.ai's GLM-4.7-Flash is a 30B-class mixture-of-experts with a 200k-token context, tuned for fast agentic use and coding, released under MIT. Available as a managed deployment: validated on AxForge hardware and deployed on a DGX Spark for your traffic only, as an OpenAI-compatible endpoint on hardware only you use, hosted in the EU.
Why GLM-4.7-Flash
| Flash means latency | A mixture-of-experts sized for speed: large-model answers at small-model latency, on a single dedicated machine. |
|---|---|
| 200k context | Long documents, long transcripts and long agent runs in one request, with 202,752 tokens of context. |
| MIT licence | No usage conditions, commercial use allowed, fine-tuning allowed. |
Specifications
| Model | GLM-4.7-Flash by zai-org |
|---|---|
| Modalities | Text |
| Sizes | 31.2B |
| Context window | 202,752 tokens |
| Released | 2026-01 |
| Popularity | 2M downloads / month on HuggingFace |
| Licence | Open weights (MIT); commercial use permitted |
| Availability | Available as managed deployment, operated by AxForge on hardware reserved for you |
| Hardware | NVIDIA DGX Spark (GB10, 128 GB unified memory), owned and operated by AxForge |
| Region | Málaga, Spain (eu-es-1) |
| Pricing | Hardware from €0.85/hour, rental term: Hour, week, month or year. Managed service quoted per deployment. Request deployment and we confirm both in writing. |
We publish only numbers we measure ourselves, and we haven't benchmarked this model on our nodes yet. For quality benchmarks, see the model card in the catalogue and the official card on HuggingFace.
Deployment
| System | A dedicated NVIDIA DGX Spark (GB10, 128 GB unified memory), reserved for you |
|---|---|
| Commercial model | Hour, week, month or year. Hardware from €0.85/hour, managed service quoted per deployment |
| Endpoint | OpenAI-compatible /v1 on your own machine, only your traffic |
| Location | Hosted in the EU: Málaga, Spain (eu-es-1) |
| Data handling | Zero prompt retention, same policy as the serverless API |
The model is validated on AxForge hardware and deployed on your system. After deployment, your endpoint speaks the OpenAI API with the model name you receive with the deployment.
Data & privacy
Prompts and completions are processed in memory in the EU, not written to disk, not logged, not retained, and never used to train anything. We keep only request metadata (token counts, timestamps, status) for billing and operations. The full policy is at axforge.ai/privacy.
FAQ
Not on the serverless API. It is available as a managed deployment: validated on AxForge hardware and deployed on a DGX Spark for your traffic only. The serverless API serves Qwen3.8 27B.
Yes, the 30B-class MoE runs on a dedicated DGX Spark; AxForge validates the build and the context length you need.
Agent workflows and coding at speed: tool calls, structured output and long context, where a fast MoE beats a slower dense model of similar quality.
We publish only numbers we measure ourselves, and we haven't benchmarked this model on our nodes yet. For quality benchmarks, see the official model card.
A dedicated NVIDIA DGX Spark (GB10, 128 GB unified memory) rented by the hour, week, month or year, running GLM-4.7-Flash behind an OpenAI-compatible endpoint on your own machine, hosted in the EU with zero prompt retention.
Hardware from €0.85/hour, by the hour, week, month or year; the managed service is quoted per deployment. Request deployment and we confirm both in writing.
Explore