Skip to content

Built-in models

The models the server knows how to fetch without an operator catalog. Each is pinned file by file, byte count and SHA-256, at a fixed revision of its Hugging Face repository, and nothing outside the binary can change a pin (Get a model, an operator catalog).

Id Repository Size Artifact
qwen3.8-27b gpillon/Qwen3.8-27B-nvfp4full-dflash2-NInfer 18.1 GiB qwen3_8_27b_nvfp4full-v2.ninfer
qwen3.8-27b-abliterated gpillon/Qwen3.8-27B-nvfp4full-dflash2-abliterated-NInfer 18.1 GiB qwen3_8_27b_nvfp4full-v2-huihui-abliterated.ninfer
qwen3.8-flash-next gpillon/Qwen3.8-Flash-Next-trellis-a25-ignis 67.8 GiB qwen3_8_flash_next_trellis_a25-v2.ninfer
ignis-image-2.1-turbo gpillon/ignis-image-2.1-turbo 15.6 GiB ignis_image_2_1_turbo-v2.ninfer
qwen3.8-27b-16g gpillon/Qwen3.8-27B-trellis-3bpw-ignis 12.5 GiB qwen3_8_27b_trellis_sc30-v2.ninfer
qwen3-asr-1.7b gpillon/Qwen3-ASR-1.7B-GGUF-ignis 1.5 GiB Qwen3-ASR-1.7B-Q4_K_M.gguf
qwen3-asr-1.7b-q8 gpillon/Qwen3-ASR-1.7B-GGUF-ignis 2.3 GiB Qwen3-ASR-1.7B-Q8_0.gguf
qwen3-asr-0.6b gpillon/Qwen3-ASR-0.6B-GGUF-ignis 0.9 GiB Qwen3-ASR-0.6B-Q8_0.gguf
nemotron-3-diarization gpillon/Nemotron-3-Diarization-GGUF-ignis 0.2 GiB Nemotron-3-Diarization-F16.gguf

gpillon/Qwen3.8-27B-nvfp4full-dflash2-NInfer at revision e961b419b672e183aa55df8c4b975abc82006e8a, 19,406,949,449 bytes in 2 files.

File Bytes SHA-256
qwen3_8_27b_nvfp4full-v2.ninfer.graft.json 6,981 b87e3c005fb1daf7d6b208da52790f95a3f478732f767f87417a5d7fc23491d1
qwen3_8_27b_nvfp4full-v2.ninfer 19,406,942,468 abb1e120d5f1f32d61689604d238227ff579ab76cbd9319628f3b3904fffd9af

gpillon/Qwen3.8-27B-nvfp4full-dflash2-abliterated-NInfer at revision ef3216949e42c42fc713feffb2e05849d57f0f3b, 19,406,984,175 bytes in 2 files.

File Bytes SHA-256
qwen3_8_27b_nvfp4full-v2-huihui-abliterated.ninfer.graft.json 41,707 09b0df892c314563192b0a4f102139939d4ef6261fcd210439d4e2636d12e6fe
qwen3_8_27b_nvfp4full-v2-huihui-abliterated.ninfer 19,406,942,468 18954280c794cb2ff1fc24ada8158de1df11bf0a0a2ea63f109045af48905ef1

gpillon/Qwen3.8-Flash-Next-trellis-a25-ignis at revision 8d94db83cd8e58d6be31e796723e5e35b960638c, 72,799,980,571 bytes in 4 files.

File Bytes SHA-256
qwen3_8_flash_next_mtp_3p0-v2.ninfer.conversion.json 179,029 a5b2c10fe0745cfe6b8e2914135e44903cfb80acb3f0db21e549e76641f14127
qwen3_8_flash_next_trellis_a25-v2.ninfer.conversion.json 1,183,942 9858d9fb03dd66fa2558b5dc6aa6463ee70f00024ffbd746545b231c9514f7a0
qwen3_8_flash_next_mtp_3p0-v2.ninfer 1,037,905,920 432fe5c0838027047c5b46c4fde526f3d3ef3d126f00fed1213921f8705988d2
qwen3_8_flash_next_trellis_a25-v2.ninfer 71,760,711,680 12e3b265b0678ba935a4b05d1b612ba4b68b3a96c3026d818ad65838985fd864

gpillon/ignis-image-2.1-turbo at revision d6912417aa47320cd71c78e19d99872faa5cb63b, 16,722,262,468 bytes in 2 files.

File Bytes SHA-256
ignis_image_2_1_turbo-v2.ninfer.conversion.json 617,924 a97f04912b9a6d76e828efc02b7e458d0f45d00bc00d794cca39d703ad0f33ca
ignis_image_2_1_turbo-v2.ninfer 16,721,644,544 4205dd1932f0801804b0a544fe1340697e4e0a0dea4a276996bcb981006050af

gpillon/Qwen3.8-27B-trellis-3bpw-ignis at revision f5bbd2cc14c9ca573ef5553c100ac69410f1fe58, 13,380,186,619 bytes in 2 files.

File Bytes SHA-256
qwen3_8_27b_trellis_sc30-v2.ninfer.conversion.json 309,495 210ab54bfe8b04e5fc4337ee3755c340ea3f21239aa625c505aa2406645a340d
qwen3_8_27b_trellis_sc30-v2.ninfer 13,379,877,124 2c4c9ee4d6b25c08da6c2d85840126e73d120564e230f926b6230b5b95ee8b3c

gpillon/Qwen3-ASR-1.7B-GGUF-ignis at revision f8a5263e398c1b3606abedc6b9c74dcbced9f93f, 1,638,144,608 bytes in 2 files.

File Bytes SHA-256
mmproj-Qwen3-ASR-1.7B-Q8_0.gguf 355,709,472 f325a44bdbc23b2df78ed35ad6342da3aabf1e618e1a9ffd1ef8861cb3b1b0f6
Qwen3-ASR-1.7B-Q4_K_M.gguf 1,282,435,136 5c5f878af090a70b25dc7a0f1090620e734654e9eceb6f4ac4656423c243974c

gpillon/Qwen3-ASR-1.7B-GGUF-ignis at revision f8a5263e398c1b3606abedc6b9c74dcbced9f93f, 2,520,744,544 bytes in 2 files.

File Bytes SHA-256
mmproj-Qwen3-ASR-1.7B-Q8_0.gguf 355,709,472 f325a44bdbc23b2df78ed35ad6342da3aabf1e618e1a9ffd1ef8861cb3b1b0f6
Qwen3-ASR-1.7B-Q8_0.gguf 2,165,035,072 9039c0cbbc13be5c25f2b34fcb70258f68f06b64f67a48831c7e13c72593e1e7

gpillon/Qwen3-ASR-0.6B-GGUF-ignis at revision af02916ea7a532a667a907c2a163b16a8c04b433, 1,019,141,984 bytes in 2 files.

File Bytes SHA-256
mmproj-Qwen3-ASR-0.6B-Q8_0.gguf 214,392,608 ee5e87436bcf8b1c550edd4300fd0516067d55b547611734d27fbc55ecaec3bc
Qwen3-ASR-0.6B-Q8_0.gguf 804,749,376 027ad3329549cd2c14e4ebd7d104e0390566e06570270c33062529474ec56015

gpillon/Nemotron-3-Diarization-GGUF-ignis at revision d46d59d03be709db18e223b6bf92e8c32d14f422, 198,805,760 bytes in 1 files.

File Bytes SHA-256
Nemotron-3-Diarization-F16.gguf 198,805,760 f7a80981d178be5d683aee225166bc03806aac2d9b629f42f418d4e5fd2c8623