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.
unsloth/Muse-Spark-Open-816B-A42B-GGUF:IQ1_Sllamacpp · IQ1_S · 163.6 GiB · quantizer (unsloth)
unsloth/Muse-Spark-Open-816B-A42B-GGUF:IQ2_XXSllamacpp · IQ2_XXS · 210.1 GiB · quantizer (unsloth)
unsloth/Muse-Spark-Open-816B-A42B-GGUF:IQ3_XXSllamacpp · IQ3_XXS · 317.0 GiB · quantizer (unsloth)
mlx-community/Muse-Spark-Open-816B-A42B-3bitmlx · 3BIT · 406.2 GiB · quantizer (mlx-community)
hf.co/Interchained/Muse-Spark-Open-816B-A42B-GGUF:Q4_0ollama · Q4_0 · 434.3 GiB · quantizer (Interchained)
inferencerlabs/Muse-Spark-Open-816B-A42B-MLX-Q4imlx · BF16 · 435.4 GiB · quantizer (inferencerlabs)
Interchained/Muse-Spark-Open-816B-A42B-GGUF:Q4_K_Mllamacpp · Q4_K_M · 465.3 GiB · quantizer (Interchained)
unsloth/Muse-Spark-Open-816B-A42B-GGUF:Q4_K_XLllamacpp · Q4_K_XL · 470.8 GiB · quantizer (unsloth)
mlx-community/Muse-Spark-Open-816B-A42B-4bitmlx · 4BIT · 496.2 GiB · quantizer (mlx-community)
unsloth/Muse-Spark-Open-816B-A42B-NVFP4vllm · NVFP4 · 496.4 GiB · quantizer (unsloth)
ggml-org/Muse-Spark-Open-816B-A42B-GGUF:Q8_0llamacpp · Q8_0 · 811.8 GiB · quantizer (ggml-org)
ggml-org/Muse-Spark-Open-816B-A42B-GGUF:BF16llamacpp · BF16 · 1527.6 GiB · quantizer (ggml-org)