MiniCPM-V 4.7 35B-A3B

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/AtomicChat/MiniCPM-V-4.7-35B-A3B-GGUF:IQ1_Mollama · IQ1_M · 9.4 GiB · quantizer (AtomicChat)

hf.co/openbmb/MiniCPM-V-4.7-35B-A3B-gguf:IQ3_XSollama · IQ3_XS · 13.5 GiB · vendor (openbmb)

hf.co/openbmb/MiniCPM-V-4.7-35B-A3B-gguf:Q3GUD_IMollama · Q3GUD_IM · 14.4 GiB · vendor (openbmb)

hf.co/openbmb/MiniCPM-V-4.7-35B-A3B-gguf:Q4_0ollama · Q4_0 · 18.4 GiB · vendor (openbmb)

hf.co/openbmb/MiniCPM-V-4.7-35B-A3B-gguf:Q4_K_Mollama · Q4_K_M · 19.7 GiB · vendor (openbmb)

mlx-community/MiniCPM-V-4.7-35B-A3B-mxfp4mlx · 4BIT · 21.0 GiB · quantizer (mlx-community)

openbmb/MiniCPM-V-4.7-35B-A3B-int4vllm · W4A16 · 21.1 GiB · vendor (openbmb)

hf.co/openbmb/MiniCPM-V-4.7-35B-A3B-gguf:Q8_0ollama · Q8_0 · 34.4 GiB · vendor (openbmb)

openbmb/MiniCPM-V-4.7-35B-A3B-FP8vllm · FP8 · 35.4 GiB · vendor (openbmb)

mlx-community/MiniCPM-V-4.7-35B-A3B-mxfp8mlx · 8BIT · 36.1 GiB · quantizer (mlx-community)

hf.co/openbmb/MiniCPM-V-4.7-35B-A3B-gguf:F16ollama · F16 · 64.6 GiB · vendor (openbmb)

openbmb/MiniCPM-V-4.7-35B-A3Bvllm · BF16 · 65.6 GiB · vendor (openbmb)

derivatives — somebody else's change to these weights

Fine-tunes, merges and abliterations of this member, each its own model with its own page. None of their numbers are counted above.

MiniCPM-V-4.7-35B-A3B-Uncensored-GGUFnot measured MiniCPM-V-4.7-35B-A3B-CRACK-GGUFnot measured MiniCPM-V-4.7-35B-A3B-MLX-4bit-TensorFoldnot measured MiniCPM-V-4.7-35B-A3B-bf16not measured MiniCPM-V-4.7-35B-A3B-OptiQ-4bitnot measured MiniCPM-V-4.7-35B-A3B-i1-GGUFnot measured MiniCPM-V-4.7-35B-A3B-MLX-Serve-4bitnot measured MiniCPM-V-4.7-35B-A3B-oQ4enot measured MiniCPM-V-4.7-35B-A3B-abliteratednot measured