Muse Glimmer 30B

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/unsloth/Muse-Glimmer-30B-GGUF:IQ2_XXSollama · IQ2_XXS · 10.0 GiB · quantizer (unsloth)

hf.co/unsloth/Muse-Glimmer-30B-GGUF:IQ2_XSollama · IQ2_XS · 10.7 GiB · quantizer (unsloth)

hf.co/unsloth/Muse-Glimmer-30B-GGUF:IQ3_XXSollama · IQ3_XXS · 12.2 GiB · quantizer (unsloth)

hf.co/meta-models/Muse-Glimmer-30B-GGUF:Q4_K_Mollama · Q4_K_M · 15.6 GiB · vendor (meta-models)

mlx-community/Muse-Glimmer-30B-4bitmlx · 4BIT · 18.1 GiB · quantizer (mlx-community)

hf.co/meta-models/Muse-Glimmer-30B-GGUF:Q4_K_XLollama · Q4_K_XL · 18.3 GiB · vendor (meta-models)

RedHatAI/Muse-Glimmer-30B-NVFP4vllm · W4A4 · 21.8 GiB · quantizer (RedHatAI)

cyankiwi/Muse-Glimmer-30B-AWQ-INT4vllm · W4A16 · 22.4 GiB · quantizer (cyankiwi)

nvidia/Muse-Glimmer-30B-NVFP4vllm · NVFP4 · 23.0 GiB · quantizer (nvidia)

mlx-community/Muse-Glimmer-30B-6bitmlx · 6BIT · 24.6 GiB · quantizer (mlx-community)

hf.co/unsloth/Muse-Glimmer-30B-GGUF:Q8_0ollama · Q8_0 · 27.6 GiB · quantizer (unsloth)

mlx-community/Muse-Glimmer-30B-8bitmlx · 8BIT · 31.1 GiB · quantizer (mlx-community)

RedHatAI/Muse-Glimmer-30B-FP8-blockvllm · FP8 · 32.0 GiB · quantizer (RedHatAI)

hf.co/NANI-Nithin/Muse-Glimmer-30B-GGUF:F16ollama · F16 · 51.9 GiB · quantizer (NANI-Nithin)

unsloth/Muse-Glimmer-30B-GGUF:BF16llamacpp · BF16 · 51.9 GiB · quantizer (unsloth)

hf.co/NANI-Nithin/Muse-Glimmer-30B-GGUF:BF16ollama · BF16 · 51.9 GiB · quantizer (NANI-Nithin)

meta-models/Muse-Glimmer-30Bvllm · BF16 · 55.5 GiB · vendor (meta-models)

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.