Full catalog
All 28 builds, including ones still downloading and two gated repos waiting on a Hugging Face sign-in. Filter by modality, license, abliteration, or which machine it fits.
| Model | Modality | Format | Params | Size | Est. memory | License | Abliterated | Status | M5 ×1 | M5 ×2 |
|---|---|---|---|---|---|---|---|---|---|---|
| Qwen3.8-27B Qwen/Qwen3.8-27B | text+vision LLM | BF16 safetensors | 27.0B | 51.77 GiB | ~62.4 GB | apache-2.0 | no | done | Quantize first | Quantize first |
| Qwen3.8 Flash-Next Qwen/Qwen3.8-Flash-Next | text+vision LLM | BF16 safetensors | 125.0B total / 6.0B active | 335.3 GiB | ~382.0 GB | qwen-community-1.0 | no | done | Quantize first | Quantize first |
| GLM-5.3-Flash zai-org/GLM-5.3-Flash | text+vision LLM | safetensors (as published) | 320.0B total / 18.0B active | 305.81 GiB | ~348.8 GB | mit | no | done | Quantize first | Quantize first |
| DeepSeek V4.1 Flash 1017 deepseek-ai/DeepSeek-V4.1-Flash-1017 | text+vision LLM | FP8/FP4 safetensors (ISTA card calls base FP8/FP4) | 763.2B total / unknown active | 475.26 GiB | ~539.8 GB | mit | no | done | Quantize first | Quantize first |
| Qwen3.8-27B unsloth/Qwen3.8-27B-GGUF | text+vision LLM | UD-Q8_K_XL GGUF + mmproj | 27.0B | 30.16 GiB | ~38.0 GB | apache-2.0 | no | done | Fits | Fits |
| Qwen3.8 Flash-Next unsloth/Qwen3.8-Flash-Next-GGUF | text+vision LLM | UD-IQ4_XS GGUF (4 shards) + mmproj | 125.0B total / 6.0B active | 88.08 GiB | ~103.3 GB | qwen-community-1.0 | no | in-progress | Fits | Fits |
| GLM-5.3-Flash unsloth/GLM-5.3-Flash-GGUF | text+vision LLM | UD-IQ2_XXS GGUF + mmproj | 320.0B total / 18.0B active | 95.93 GiB | ~112.2 GB | mit | no | queued | Tight / offload | Fits |
| DeepSeek V4.1 Flash 1017 ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF | text+vision LLM | GSQ-RCO IQ1_M backbone + shared Engram IQ4_NL + mmproj | 763.2B total / unknown active | 216.34 GiB | ~130.8 GB | mit | no | queued | No | Fits |
| Qwen3.8-27B alesha-pro/Qwen3.8-27B-S-mirai-GGUF | text+vision LLM | Mirai S 2.4-bit GGUF + mmproj + refusal control vector | 27.0B | 11.27 GiB | ~16.7 GB | apache-2.0 | abliterated | done | Fits | Fits |
| Qwen3.8 Flash-Next alesha-pro/Qwen3.8-Flash-Next-abliterated-GSQ-RCO-Strata-GGUF | text+vision LLM | GSQ-RCO IQ3_S GGUF + mmproj + refusal vector | 125.0B total / 6.0B active | 78.72 GiB | ~92.8 GB | qwen-community-license-1.0 | abliterated | done | Fits | Fits |
| GLM-5.3-Flash alesha-pro/GLM-5.3-Flash-abliterated-Maya-M-GGUF | text+vision LLM | Maya-M IQ2_S GGUF + vision + refusal vector | 320.0B total / 18.0B active | 109.1 GiB | ~127.0 GB | mit | abliterated | done | No | No |
| Qwen3.8-27B huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF | text+vision LLM | Q4_K GGUF + mmproj | 27.0B | 16.52 GiB | ~22.6 GB | apache-2.0 | abliterated | done | Fits | Fits |
| Qwen3.8-27B huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF | text+vision LLM | BF16 GGUF + mmproj | 27.0B | 51.77 GiB | ~62.4 GB | apache-2.0 | abliterated | done | Fits | Fits |
| Qwen3.8 Flash-Next huihui-ai/Huihui-Qwen3.8-Flash-Next-abliterated-v2-GGUF | text+vision LLM | UD-Q4_K_XL V2 GGUF (4 shards) + mmproj | 125.0B total / 6.0B active | 105.63 GiB | ~123.1 GB | qwen-community-1.0 | abliterated | done | No | Fits |
| GLM-5.3-Flash huihui-ai/Huihui-GLM-5.3-Flash-abliterated-GGUF | text+vision LLM | UD-IQ2_XXS GGUF + mmproj | 320.0B total / 18.0B active | 95.93 GiB | ~112.2 GB | mit | abliterated | queued | Tight / offload | Fits |
| DeepSeek V4.1 Flash 1017 huihui-ai/Huihui-DeepSeek-V4.1-Flash-1017-abliterated-GGUF | text+vision LLM | UD-IQ1_M GGUF (5 shards) + mmproj | 763.2B total / unknown active | 234.11 GiB | ~267.9 GB | mit | abliterated | done | No | No |
| Whisper large-v3-turbo openai/whisper-large-v3-turbo | speech-to-text | safetensors | 0.809B | 1.51 GiB | ~5.6 GB | mit | no | queued | Fits | Fits |
| Qwen3-TTS 1.7B Base Qwen/Qwen3-TTS-12Hz-1.7B-Base | text-to-speech (voice clone) | safetensors | 1.93B | 4.23 GiB | ~8.5 GB | apache-2.0 | no | queued | Fits | Fits |
| Fish Audio S2 Pro fishaudio/s2-pro | text-to-speech | safetensors | 4.56B | 10.26 GiB | ~15.0 GB | fish-audio-research-license non-commercial | no | queued | Fits | Fits |
| ACE-Step 1.5 ACE-Step/Ace-Step1.5 | text-to-music | safetensors (turbo DiT + LM) | unknown | 9.4 GiB | ~8.0 GB | mit | no | queued | Fits | Fits |
| YuE2 (ComfyUI repack) Comfy-Org/YuE2 | lyrics-to-music | bf16 safetensors (ComfyUI) | 3.0B | 12.24 GiB | ~17.1 GB | cc-by-nc-4.0 non-commercial | no | queued | Fits | Fits |
| Qwen-Image 2.1 Qwen/Qwen-Image-2.1 | text-to-image + editing | safetensors (as published) | 7.1B | 30.86 GiB | ~37.1 GB | qwen-research non-commercial | no | in-progress | Fits | Fits |
| MOSS-Image Base OpenMOSS-Team/MOSS-Image-Base | text-to-image | safetensors (as published) | unknown | 25.36 GiB | ~31.2 GB | apache-2.0 | no | queued | Fits | Fits |
| Wan 2.2 T2V A14B Wan-AI/Wan2.2-T2V-A14B | text-to-video | safetensors (as published) | unknown | 117.53 GiB | ~130.2 GB | apache-2.0 | no | queued | Tight / offload | Tight / offload |
| Wan 2.2 I2V A14B Wan-AI/Wan2.2-I2V-A14B | image-to-video | safetensors (as published) | unknown | 117.54 GiB | ~130.2 GB | apache-2.0 | no | queued | Tight / offload | Tight / offload |
| HunyuanVideo 1.5 tencent/HunyuanVideo-1.5 | text/image-to-video | safetensors (as published) | 8.3B | 346.24 GiB | unknown | tencent-hunyuan-community | no | queued | Fits | Fits |
| FLUX.3 Klein (ComfyUI) black-forest-labs/flux-3-image-klein-comfy | image generation/editing | unknown (gated) | unknown | 87.28 GiB | unknown | flux-kommunity-license | no | needs-Ian | Unknown | Unknown |
| LTX-2.5 Lightricks/LTX-2.5 | image/text-to-video | unknown (gated) | unknown | 187.06 GiB | unknown | ltx-2.x-community-license-agreement | no | needs-Ian | Unknown | Unknown |
"needs-Ian" = gated repo; the owner has to accept the publisher's terms on Hugging Face first. Machine-readable: data/catalog.json.