GLM-4.6V-Flash
Official · BF16 · safetensors
Runtime certified: SGLang Transformers vLLM
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
GLM · Vision · GLM-4.6V
GLM-4.6V Flash: Specs, GPU requirements, hosting & deployment
GLM-4.6V Flash is a current Vision release in the GLM family, certified from its immutable official source revision.
Total parameters10.3B
Active parametersDense model
Context window131,072 tokens
Release statusCurrent · Current
ArchitectureGlm4vForConditionalGeneration
ModalitiesMultimodal
Licensemit
Deployment stateDeployable with certified configuration
Commercial stateCommercial Use Allowed
Release date2025-12-07
Architecture, strengths and use cases
GLM-4.6V Flash is an official self-hostable Z.ai release in the GLM Vision track. It uses Glm4vForConditionalGeneration, carries 10.29B, supports a verified context window of 131,072 tokens, and exposes only source-certified checkpoints and runtime combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
GLM-4.6V Flash uses Glm4vForConditionalGeneration with 10.29B. The stored architecture profile records 40 layers, hidden width 4096, 32 attention heads and a 131,072 token context ceiling where the official configuration publishes those fields.
Verified Glm4vForConditionalGeneration architecture
131,072 token certified context
Official BF16 checkpoint coverage
Private LLM inference
Agentic workflows
Long-context document processing
Certified checkpoints and quantizations
Only exact, source-certified variants attached to this release are shown.
Recommended hardware
Use only the listed transformers, vllm, sglang runtime configuration with the exact checkpoint precision. The recommendation engine checks weight memory, KV cache, runtime overhead, safety headroom, GPU architecture and topology before ranking rentable and reference hardware.
Estimated weight memory19.74 GB
KV cache0.31 GB
Runtime overhead8.33 GB
Total with safety margin35.2 GB
Recommended best value
1× NVIDIA H200 SXM 141GB
141 GB total VRAM · nvswitch
105.8 GB headroom · Limited capacity
USD 2,345 / monthLowest-cost viable
2× NVIDIA L4 24GB
48 GB total VRAM · pcie
12.8 GB headroom · Available
USD 500 / monthHighest performance
1× NVIDIA H200 SXM 141GB
141 GB total VRAM · nvswitch
105.8 GB headroom · Limited capacity
USD 2,345 / monthLicense and self-hosting considerations
The full 10.29B resident weight set must fit across the selected GPUs. Context and concurrency add KV-cache memory; MoE active parameters do not replace resident-weight memory.
GLM-4.6V Flash is published under mit. The release-scoped official license link and verification date are retained with the catalogue record.
Commercial Use Allowed. The official license permits commercial use; its obligations still apply.
Alternatives and sibling variants
GLM-4.6V, GLM-4.5V
Release timeline
zai/glm/glm-4-6v-flash
Source details
Source revision: 01889dafc2091bf309d7e0a6671c37c0cfe0602819c9dd67c4a2ceac055056e6
Frequently asked questions
How much VRAM does GLM-4.6V Flash require?
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible runtime configurations.
Which runtimes support GLM-4.6V Flash?
Certified upstream runtime evidence is available for transformers, vllm, sglang.
Can GLM-4.6V Flash be used commercially?
The stored commercial classification is Commercial Use Allowed. Consult the official mit terms for the final obligations.
Official references
Last verified: 2026-09-03