SmolLM3 3B

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/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF:IQ2_Mollama · IQ2_M · 1.0 GiB · quantizer (bartowski)

hf.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF:IQ3_XXSollama · IQ3_XXS · 1.2 GiB · quantizer (bartowski)

hf.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF:Q3_K_Lollama · Q3_K_L · 1.6 GiB · quantizer (bartowski)

mlx-community/SmolLM3-3B-4bitmlx · 4BIT · 1.6 GiB · quantizer (mlx-community)

hf.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF:Q4_0ollama · Q4_0 · 1.7 GiB · quantizer (bartowski)

hf.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF:Q4_K_Mollama · Q4_K_M · 1.8 GiB · quantizer (bartowski)

lmstudio-community/SmolLM3-3B-MLX-6bitmlx · 6BIT · 2.3 GiB · quantizer (lmstudio-community)

lmstudio-community/SmolLM3-3B-MLX-8bitmlx · 8BIT · 3.0 GiB · quantizer (lmstudio-community)

hf.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF:Q8_0ollama · Q8_0 · 3.0 GiB · quantizer (bartowski)

RedHatAI/SmolLM3-3B-FP8-dynamicvllm · FP8 · 3.1 GiB · quantizer (RedHatAI)

HuggingFaceTB/SmolLM3-3Bvllm · BF16 · 5.7 GiB · vendor (HuggingFaceTB)

hf.co/bartowski/HuggingFaceTB_SmolLM3-3B-GGUF:BF16ollama · BF16 · 5.7 GiB · quantizer (bartowski)

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.