Hunyuan MT 2 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/unsloth/Hy-MT2-7B-GGUF:IQ2_Mollama · IQ2_M · 2.6 GiB · quantizer (unsloth)

hf.co/unsloth/Hy-MT2-7B-GGUF:IQ3_XXSollama · IQ3_XXS · 2.9 GiB · quantizer (unsloth)

hf.co/unsloth/Hy-MT2-7B-GGUF:IQ4_XSollama · IQ4_XS · 3.9 GiB · quantizer (unsloth)

hf.co/tencent/Hy-MT2-7B-GGUF:Q4_K_Mollama · Q4_K_M · 4.3 GiB · vendor (tencent)

shawnw3i/Hy-MT2-7B-AWQvllm · AWQ · 4.4 GiB · quantizer (shawnw3i)

hf.co/tencent/Hy-MT2-7B-GGUF:Q6_Kollama · Q6_K · 5.7 GiB · vendor (tencent)

hf.co/tencent/Hy-MT2-7B-GGUF:Q8_0ollama · Q8_0 · 7.4 GiB · vendor (tencent)

tencent/Hy-MT2-7B-FP8vllm · FP8 · 7.5 GiB · vendor (tencent)

hf.co/unsloth/Hy-MT2-7B-GGUF:BF16ollama · BF16 · 14.0 GiB · quantizer (unsloth)

tencent/Hy-MT2-7Bvllm · 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.

Hy-MT2-7B-int4-AutoRoundnot measured Hy-MT2-7B-4bitnot measured Hy-MT2-7B-Abliterated-bf16not measured Hy-MT2-7B-i1-GGUFnot measured