Hunyuan MT 1.5 7B

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-MT1.5-7B-GGUF:Q2_Kollama · Q2_K · 2.8 GiB · quantizer (mradermacher)

hf.co/mradermacher/HY-MT1.5-7B-GGUF:Q3_K_Sollama · Q3_K_S · 3.2 GiB · quantizer (mradermacher)

hf.co/mradermacher/HY-MT1.5-7B-GGUF:Q3_K_Lollama · Q3_K_L · 3.8 GiB · quantizer (mradermacher)

mlx-community/HY-MT1.5-7B-4bitmlx · 4BIT · 3.9 GiB · quantizer (mlx-community)

hf.co/tencent/HY-MT1.5-7B-GGUF:Q4_K_Mollama · Q4_K_M · 4.3 GiB · vendor (tencent)

tencent/HY-MT1.5-7B-GPTQ-Int4vllm · GPTQ · 4.5 GiB · vendor (tencent)

mlx-community/HY-MT1.5-7B-6bitmlx · 6BIT · 5.7 GiB · quantizer (mlx-community)

hf.co/tencent/HY-MT1.5-7B-GGUF:Q6_Kollama · Q6_K · 5.7 GiB · vendor (tencent)

mlx-community/HY-MT1.5-7B-8bitmlx · 8BIT · 7.4 GiB · quantizer (mlx-community)

hf.co/tencent/HY-MT1.5-7B-GGUF:Q8_0ollama · Q8_0 · 7.4 GiB · vendor (tencent)

tencent/HY-MT1.5-7B-FP8vllm · FP8 · 7.5 GiB · vendor (tencent)

hf.co/mradermacher/HY-MT1.5-7B-GGUF:F16ollama · F16 · 14.0 GiB · quantizer (mradermacher)

tencent/HY-MT1.5-7Bvllm · BF16 · 15.0 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.

Huihui-HY-MT1.5-7B-abliteratednot measured HY-MT1.5-7B-mlx-fp16not measured HY-MT1.5-7B-bf16not measured