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/MiniCPM4.1-8B-Russian-CPT-i1-GGUF:IQ1_Sollama · IQ1_S · 1.7 GiB · quantizer (mradermacher)
hf.co/mradermacher/MiniCPM4.1-8B-Russian-CPT-i1-GGUF:IQ2_XXSollama · IQ2_XXS · 2.1 GiB · quantizer (mradermacher)
hf.co/mradermacher/MiniCPM4.1-8B-Russian-CPT-i1-GGUF:IQ3_XXSollama · IQ3_XXS · 3.0 GiB · quantizer (mradermacher)
mlx-community/MiniCPM4.1-8B-4bitmlx · 4BIT · 4.3 GiB · quantizer (mlx-community)
openbmb/MiniCPM4.1-8B-MLXvllm · 4BIT · 4.3 GiB · vendor (openbmb)
hf.co/mradermacher/MiniCPM4.1-8B-Russian-CPT-i1-GGUF:Q4_0ollama · Q4_0 · 4.4 GiB · quantizer (mradermacher)
hf.co/openbmb/MiniCPM4.1-8B-GGUF:Q4_K_Mollama · Q4_K_M · 4.6 GiB · vendor (openbmb)
openbmb/MiniCPM4.1-8B-AutoAWQvllm · AWQ · 4.8 GiB · vendor (openbmb)
mlx-community/MiniCPM4.1-8B-6bitmlx · 6BIT · 6.2 GiB · quantizer (mlx-community)
mlx-community/MiniCPM4.1-8B-8bitmlx · 8BIT · 8.1 GiB · quantizer (mlx-community)
hf.co/mradermacher/MiniCPM4.1-8B-Russian-CPT-GGUF:Q8_0ollama · Q8_0 · 8.1 GiB · quantizer (mradermacher)
openbmb/MiniCPM4.1-8Bvllm · BF16 · 15.2 GiB · vendor (openbmb)
hf.co/mradermacher/MiniCPM4.1-8B-Russian-CPT-GGUF:F16ollama · F16 · 15.2 GiB · quantizer (mradermacher)