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/stepfun-ai_Step-3.5-Flash-GGUF:IQ1_Sollama · IQ1_S · 38.5 GiB · quantizer (bartowski)
bartowski/stepfun-ai_Step-3.5-Flash-GGUF:IQ2_XSllamacpp · IQ2_XS · 51.4 GiB · quantizer (bartowski)
bartowski/stepfun-ai_Step-3.5-Flash-GGUF:IQ3_XXSllamacpp · IQ3_XXS · 72.8 GiB · quantizer (bartowski)
hf.co/mradermacher/Step-3.5-Flash-GGUF:Q3_K_Sollama · Q3_K_S · 79.2 GiB · quantizer (mradermacher)
bartowski/stepfun-ai_Step-3.5-Flash-GGUF:Q3_K_Lllamacpp · Q3_K_L · 87.3 GiB · quantizer (bartowski)
mlx-community/Step-3.5-Flash-4bitmlx · 4BIT · 103.2 GiB · quantizer (mlx-community)
hf.co/mradermacher/Step-3.5-Flash-GGUF:Q4_K_Sollama · Q4_K_S · 103.8 GiB · quantizer (mradermacher)
stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S:Q4_K_Sllamacpp · Q4_K_S · 103.8 GiB · vendor (stepfun-ai)
amd/Step-3.5-Flash-MXFP4vllm · QUARK · 106.6 GiB · quantizer (amd)
hf.co/mradermacher/Step-3.5-Flash-GGUF:Q4_K_Mollama · Q4_K_M · 110.4 GiB · quantizer (mradermacher)
hf.co/ggml-org/Step-3.5-Flash-GGUF:Q4_Kollama · Q4_K · 110.6 GiB · quantizer (ggml-org)
bartowski/stepfun-ai_Step-3.5-Flash-GGUF:Q4_K_Mllamacpp · Q4_K_M · 111.7 GiB · quantizer (bartowski)
mlx-community/Step-3.5-Flash-6bitmlx · 6BIT · 149.0 GiB · quantizer (mlx-community)
stepfun-ai/Step-3.5-Flash-FP8vllm · FP8 · 194.2 GiB · vendor (stepfun-ai)
mlx-community/Step-3.5-Flash-8bitmlx · 8BIT · 194.9 GiB · quantizer (mlx-community)
stepfun-ai/Step-3.5-Flash-GGUF-Q8_0:Q8_0llamacpp · Q8_0 · 195.0 GiB · vendor (stepfun-ai)
stepfun-ai/Step-3.5-Flashvllm · BF16 · 371.4 GiB · vendor (stepfun-ai)