Hunyuan MT 1.5 1.8B

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/mradermacher/HY-MT1.5-1.8B-GGUF:Q2_Kollama · Q2_K · 0.7 GiB · quantizer (mradermacher)

hf.co/mradermacher/HY-MT1.5-1.8B-GGUF:Q3_K_Sollama · Q3_K_S · 0.8 GiB · quantizer (mradermacher)

mlx-community/HY-MT1.5-1.8B-4bitmlx · 4BIT · 0.9 GiB · quantizer (mlx-community)

hf.co/mradermacher/HY-MT1.5-1.8B-GGUF:Q3_K_Lollama · Q3_K_L · 0.9 GiB · quantizer (mradermacher)

hf.co/tencent/HY-MT1.5-1.8B-GGUF:Q4_K_Mollama · Q4_K_M · 1.1 GiB · vendor (tencent)

tencent/HY-MT1.5-1.8B-GPTQ-Int4vllm · GPTQ · 1.2 GiB · vendor (tencent)

mlx-community/HY-MT1.5-1.8B-6bitmlx · 6BIT · 1.4 GiB · quantizer (mlx-community)

hf.co/tencent/HY-MT1.5-1.8B-GGUF:Q6_Kollama · Q6_K · 1.4 GiB · vendor (tencent)

mlx-community/HY-MT1.5-1.8B-8bitmlx · 8BIT · 1.8 GiB · quantizer (mlx-community)

hf.co/tencent/HY-MT1.5-1.8B-GGUF:Q8_0ollama · Q8_0 · 1.8 GiB · vendor (tencent)

tencent/HY-MT1.5-1.8B-FP8vllm · FP8 · 1.9 GiB · vendor (tencent)

hf.co/mradermacher/HY-MT1.5-1.8B-GGUF:F16ollama · F16 · 3.3 GiB · quantizer (mradermacher)

tencent/HY-MT1.5-1.8Bvllm · BF16 · 3.8 GiB · vendor (tencent)

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.

Hy-MT1.5-1.8B-1.25bitnot measured Huihui-HY-MT1.5-1.8B-abliteratednot measured HY-MT1.5-1.8B-mlx-fp16not measured HY-MT1.5-1.8B-bf16not measured HY-MT1.5-1.8B-i1-GGUFnot measured HY-MT1.5-1.8B-GGUFnot measured