No machine on this network has measured this model yet. Everything below is what the catalog knows exists — where the weights come from, how large each build is, and whose work it is. Nothing here is a claim about what the model can do; that only appears once a machine has run it and signed the result.
hf.co/mradermacher/GLM-OCR-GGUF:Q2_Kollama · Q2_K · 0.3 GiB · quantizer (mradermacher)
hf.co/mradermacher/GLM-OCR-GGUF:Q3_K_Sollama · Q3_K_S · 0.4 GiB · quantizer (mradermacher)
hf.co/mradermacher/GLM-OCR-GGUF:Q3_K_Lollama · Q3_K_L · 0.4 GiB · quantizer (mradermacher)
hf.co/mradermacher/GLM-OCR-GGUF:Q4_K_Sollama · Q4_K_S · 0.5 GiB · quantizer (mradermacher)
hf.co/mradermacher/GLM-OCR-GGUF:Q4_K_Mollama · Q4_K_M · 0.5 GiB · quantizer (mradermacher)
hf.co/ggml-org/GLM-OCR-GGUF:Q8_0ollama · Q8_0 · 0.9 GiB · quantizer (ggml-org)
EZCon/GLM-OCR-4bit-mlxmlx · 4BIT · 1.2 GiB · quantizer (EZCon)
AlphaOxO/GLM-OCR-NVFP4vllm · W4A16 · 1.3 GiB · quantizer (AlphaOxO)
EZCon/GLM-OCR-8bit-mlxmlx · 8BIT · 1.5 GiB · quantizer (EZCon)
hf.co/ggml-org/GLM-OCR-GGUF:F16ollama · F16 · 1.7 GiB · quantizer (ggml-org)