547 5 months ago

vision tools thinking
ollama run ucx0204/glm-4.6V-Flash-Q8

Details

5 months ago

1e43920e24a6 · 12GB ·

glm4
·
9.4B
·
Q8_0
clip
·
892M
·
F16
[gMASK]<sop> {{- if .Tools }}<|system|> # Tools You may call one or more functions to assist with th
{ "num_ctx": 65556, "repeat_penalty": 1.1, "stop": [ "<|system|>", "<|us

Readme

GLM-4.6V-Flash (Q8_0 GGUF)

This is a GGUF version of the GLM-4.6V-Flash model, quantized to Q8_0 (8-bit) for high-quality inference. It originates from Zhipu AI and was converted/quantized by Unsloth.

🚀 Model Details

  • Original Model: Zhipu AI GLM-4.6V-Flash
  • Quantization: Q8_0 (8-bit) - High quality, balanced memory usage.
  • Format: GGUF (Compatible with Ollama)
  • Capabilities: Multimodal (Vision & Text), Flash attention for speed.
  • Source: unsloth/GLM-4.6V-Flash-GGUF