GLM-4.6V-Flash
GLM-4.6V-Flash is an open-weights language model from Z.ai, released December 8, 2025. It has 10B parameters (dense). The context window is 125K tokens. API price: $0 input / $0 output per million tokens.
Check it against your own PC →
Can you run GLM-4.6V-Flash locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, split GPU / CPU, roughly 5 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Runs, slowly | Q6_K (≈ lossless) | 5.2 GB | 4.5 GB | ~5 |
| 8 GB VRAM | Runs on GPU | IQ4_XS (good) | 6.7 GB | – | ~29 |
| 12 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 9.7 GB | – | ~25 |
| 16 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 9.7 GB | – | ~34 |
| 24 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 9.7 GB | – | ~62 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 9.7 GB | – | ~110 |
Ready-made quantizations on Hugging Face: unsloth/GLM-4.6V-Flash-GGUF · lmstudio-community/GLM-4.6V-Flash-GGUF · bartowski/zai-org_GLM-4.6V-Flash-GGUF · ggml-org/GLM-4.6V-Flash-GGUF · MaziyarPanahi/GLM-4.6V-Flash-GGUF · mradermacher/GLM-4.6V-Flash-GGUF
Benchmark results
Epoch AI has not published results for GLM-4.6V-Flash yet. New models are usually evaluated within days to weeks.
Links
Hugging Face: zai-org/GLM-4.6V-Flash
More from Z.ai
GLM-5.3-FlashX · GLM 5.3 Flash BF16 · GLM 5.3 BF16 · GLM-5.3-Flash · GLM-5.3 · GLM-5.2 · GLM-5.1 · GLM-5V-Turbo