AI๊ฐ ์์ง์ด๊ณ ๋ฏธ๋๊ฐ ์
๋ฐ์ดํธ๋ฉ๋๋ค.MiniMax-H3-TextEncoder-Qwen3VL-32B-abliterated-GGUF
> ๐ **Newer, better-quality build:** pottokao/MiniMax-H3-TextEncoder-16GB-GGUF โ official encoder weights, quantized per tensor by how much each one affects the H3 DiT, K-quants only. At the same 12.65 GB `_vis` size its conditioning error is about half of this Q3_K_S (7.9% vs 14.4%), with 13.7 / 14.8 GB options at 6.4% / 4.9%. > โ ๏ธ The `_vis` file here stores the visual tower's 5-D `patch_embed` weight as-is; recent `gguf` versions refuse tensors with more than 4 dimensions, so it may fail to load on an up-to-date ComfyUI-GGUF. The new repo stores it the ComfyUI-GGUF way. > ๐ ๆๆฐ็๏ผpottokao/MiniMax-H3-TextEncoder-16GB-GGUF๏ผๅฎๆนๆฌ้ใไพ H3 DiT ๆๆๅบฆ้ๅผต้้ๅใๅช็จ K ็ณปๅ๏ผใๅๆจฃ 12.65 GB ่ชคๅทฎ็ด็บ้้ก็ไธๅใ้่ฃก็ `_vis` ๆชๅจๆฐ็ gguf ๅฅไปถไธๅฏ่ฝ่ผไธ้ฒๅปใ > ๐ Heads-up: I've been focused on still-image work lately, so I don't have the bandwidth to help with video setups like MiniMax-H3 for now. The files stay up as they are โ thanks for understanding! > ๆ่ฟ้ๅฟๆพๅจๅนณ้ขๆๅฝฑ๏ผๅฝฑ็้ก๏ผๅ MiniMax-H3๏ผๆซๆๆฏ่ผๆฒ่พฆๆณๅๅฉๆ้ฏใๆชๆกๆ็ ง่็่๏ผ่ฌ่ฌ้ซ่ซ๏ผ GGUF (llama.cpp) builds of the **MiniMax-H3 text encoder** โ abliterated Qwen3-VL-32B, 50 layers, **Q3_K_S** (โ3.53 BPW).
๋ฒ์ญ ์ค๋น ์ค์ ๋๋ค. ์๋ฌธ์ ํ์ํฉ๋๋ค.
> ๐ **Newer, better-quality build:** pottokao/MiniMax-H3-TextEncoder-16GB-GGUF โ official encoder weights, quantized per tensor by how much each one affects the H3 DiT, K-quants only. At the same 12.65 GB `_vis` size its conditioning error is about half of this Q3_K_S (7.9% vs 14.4%), with 13.7 / 14.8 GB options at 6.4% / 4.9%. > โ ๏ธ The `_vis` file here stores the visual tower's 5-D `patch_embed` weight as-is; recent `gguf` versions refuse tensors with more than 4 dimensions, so it may fail to load on an up-to-date ComfyUI-GGUF. The new repo stores it the ComfyUI-GGUF way. > ๐ ๆๆฐ็๏ผpottokao/MiniMax-H3-TextEncoder-16GB-GGUF๏ผๅฎๆนๆฌ้ใไพ H3 DiT ๆๆๅบฆ้ๅผต้้ๅใๅช็จ K ็ณปๅ๏ผใๅๆจฃ 12.65 GB ่ชคๅทฎ็ด็บ้้ก็ไธๅใ้่ฃก็ `_vis` ๆชๅจๆฐ็ gguf ๅฅไปถไธๅฏ่ฝ่ผไธ้ฒๅปใ > ๐ Heads-up: I've been focused on still-image work lately, so I don't have the bandwidth to help with video setups like MiniMax-H3 for now. The files stay up as they are โ thanks for understanding! > ๆ่ฟ้ๅฟๆพๅจๅนณ้ขๆๅฝฑ๏ผๅฝฑ็้ก๏ผๅ MiniMax-H3๏ผๆซๆๆฏ่ผๆฒ่พฆๆณๅๅฉๆ้ฏใๆชๆกๆ็ ง่็่๏ผ่ฌ่ฌ้ซ่ซ๏ผ GGUF (llama.cpp) builds of the **MiniMax-H3 text encoder** โ abliterated Qwen3-VL-32B, 50 layers, **Q3_K_S** (โ3.53 BPW).