GLM-4.5V
This model is part of the GLM-V family of models, introduced in the paper GLM-4.1V-Thinking and GLM-4.5V: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.
Params
107.7 B
Context
—
Downloads 30d
26 K
Likes
726
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)26 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 215.4 GB | 253.6 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.60
input / 1M
$1.80
output / 1M
$0.11
cached input / 1M
$2.40
1M in + 1M out
- Context window
- 65,536 tokens
- Max output
- 16,384 tokens
- Providers
- 2
- Cheapest provider
- Novita · $0.60 / $1.80
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 7.6 / — / —
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✓ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- Glm4vMoeForConditionalGeneration
- Parameters
- 107.7 B
- Tensor type
- BF16
- Licence
- mit
- First seen on the Hub
- 2025-08-10
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any image-text-to-text model