Model Gallery

38 models from 1 repositories

Filter by type:

Filter by tags:

humanizer-12b-bf16
Humanizer is a 12B Gemma 4 fine-tune for rewriting English and Chinese text. This unquantized BF16 GGUF build uses llama.cpp with an 8,192-token context. This entry uses the completions API with the publisher's exact rewriting prompt.

Repository: localaiLicense: apache-2.0

spark-s1-4b-v6
spark-s1-4b-v6 is a Qwen3.5-4B decision model (Open Spark Jev): given a state and a question with a fixed menu of options it returns a calibrated probability per option from the first-token logprobs of the option letters. It is not a chat model: send the rendered prompt to /v1/completions with max_tokens 1, logprobs true, and top_logprobs 20. Check that every option letter appears in the returned probabilities. Then apply softmax(logprob / 1.481) over those letters. Q8_0 GGUF (agrees with the bf16 model on 99.5% of held-out decisions).

Repository: localaiLicense: apache-2.0

ornith-1.5-9b-uncensored
# Ornith-1.5-9B-uncensored An **abliterated** (refusal-direction-ablated) build of `ornith-ai/Ornith-1.5-9B`, produced with ZeroFuse and published by junafinity. This is the **9B control checkpoint** (bf16). Mac users should start from the MLX-8bit or GGUF-8bit siblings. The official 9B base has **no `mtp.*` tensors**; nothing was grafted. **Vision tower and MTP heads are preserved** — see Vision & MTP preservation for the before/after audit. ## Intended use: red teaming and defensive cybersecurity research These uncensored (abliterated) weights are built as a **research instrument** for red teaming and defensive cybersecurity work. Safety training suppresses the *display* of capability, not capability itself. A refusal tells you the model declined. It does not tell you whether the weights could have complied. That conflation underestimates the true ceiling and hides holes in *your* filters, classifiers, and policy layer. Use each uncensored checkpoint as the **treatment half of a controlled pair** against its original base model: ...

Repository: localaiLicense: apache-2.0

llm-jp-4-33b-thinking-bf16
LLM-jp-4-33B-thinking in the official 66.4 GB BF16 GGUF format. This variant preserves the original model precision for hosts with enough memory.

Repository: localaiLicense: apache-2.0

neohorse-1-4b-bf16
NeoHorse-1-4B is TokenRhythm's text-only Qwen3.5-4B fine-tune for coding, reasoning, and agentic tasks. This official BF16 GGUF build uses the embedded Jinja chat template and a 32K-token default context.

Repository: localaiLicense: apache-2.0

qwen3-coder-30b-a3b-vllm-cpp
Qwen3-Coder-30B-A3B on vllm.cpp: a coding and agentic-tool-use model, 30B total parameters with about 3B active per token, gated token-exact against vLLM on this engine. The tool-call parser is named explicitly rather than auto-detected, and that matters here. Qwen3-Coder's tool dialect is byte-identical on the wire to another family's, so template sniffing cannot separate the two and would fall back to the wrong parser. With qwen3_coder named, tool calls arrive as real tool_calls on the OpenAI response. This is the bf16 checkpoint, roughly 57 GB of weights, which is what the engine was gated on. Being bf16 rather than NVFP4 it does not need Blackwell on its own account, but LocalAI's CUDA images for this backend are currently built for Blackwell-family GPUs only, so on an older card use the CPU build.

Repository: localaiLicense: apache-2.0

qwen3-4b-vllm-cpp
Qwen3-4B on vllm.cpp, in bf16. The small end of the engine's gated dense family, which reaches parity with vLLM on every axis at concurrency 1. bf16 rather than NVFP4 on purpose: this is the entry that runs where the flagship NVFP4 checkpoints cannot, including Apple Silicon via Metal, Vulkan and plain CPU. Roughly 8 GB of weights, plus about 4.5 GB of KV cache at the context configured here. Tool calling and the thinking split are parsed inside the engine.

Repository: localaiLicense: apache-2.0

qwen3-0.6b-vllm-cpp
Qwen3-0.6B on vllm.cpp, in bf16. Roughly 1.4 GB of weights, which makes it the cheapest way to confirm a vllm-cpp install actually serves before committing disk and memory to one of the large checkpoints. It runs anywhere the backend does, CPU included, and it is a real chat model rather than a stub, so tool calling and the thinking split can be exercised on it too.

Repository: localaiLicense: apache-2.0

minimax-h3-fl2va-unpruned-q4
MiniMax-H3 served by vllm.cpp, LocalAI's own C++ port of vLLM. It generates video AND audio jointly, so a clip comes back as an MP4 with a soundtrack. Ask for speech in the prompt and the model lip-syncs it. Runtime: vllm.cpp (backend vllm-cpp). Partition: fl2va. DiT layout: unpruned. Format: Q4_K_M. This entry is the FL2VA partition, which serves text-to-video (t2va) and first/last-frame conditioning (fl2va). It refuses reference conditioning: for that use the matching ref2va entry. The DiT is the original time-embedder DiT (~19.9 GB). Render status: verified render (end to end on the vllm.cpp model page). Q3_K_M of the same DiT is verified BAD and is not offered. The vllm.cpp page records its renders with the DiT expanded to bf16. This entry does not expand it and keeps the quantised weights resident, so a render in that mode is not covered by the page. The weights are one DiT, the Qwen3-VL-32B encoder (~14.6 GB), the video VAE (~10.4 GB), the audio VAE and the tokenizer, plus the two VAE configs that carry the latent statistics. The default canvas is 1344x768 at 124 frames and 24 fps, about 5.2 seconds. Generation is slow: roughly 176 s per denoise step at that canvas on a 20-SM device. Muxing the finished frames needs ffmpeg on the host.

Repository: localaiLicense: other

minimax-h3-fl2va-q4
MiniMax-H3 served by vllm.cpp, LocalAI's own C++ port of vLLM. It generates video AND audio jointly, so a clip comes back as an MP4 with a soundtrack. Ask for speech in the prompt and the model lip-syncs it. Runtime: vllm.cpp (backend vllm-cpp). Partition: fl2va. DiT layout: unpruned. Format: Q4_K_M. This entry is the FL2VA partition, which serves text-to-video (t2va) and first/last-frame conditioning (fl2va). It refuses reference conditioning: for that use the matching ref2va entry. The DiT is the original time-embedder DiT (~19.9 GB). Render status: verified render (end to end on the vllm.cpp model page). Q3_K_M of the same DiT is verified BAD and is not offered. The vllm.cpp page records its renders with the DiT expanded to bf16. This entry does not expand it and keeps the quantised weights resident, so a render in that mode is not covered by the page. The weights are one DiT, the Qwen3-VL-32B encoder (~14.6 GB), the video VAE (~10.4 GB), the audio VAE and the tokenizer, plus the two VAE configs that carry the latent statistics. The default canvas is 1344x768 at 124 frames and 24 fps, about 5.2 seconds. Generation is slow: roughly 176 s per denoise step at that canvas on a 20-SM device. Muxing the finished frames needs ffmpeg on the host.

Repository: localaiLicense: other

minimax-h3-ref2va-unpruned-q4
MiniMax-H3 served by vllm.cpp, LocalAI's own C++ port of vLLM. It generates video AND audio jointly, so a clip comes back as an MP4 with a soundtrack. Ask for speech in the prompt and the model lip-syncs it. Runtime: vllm.cpp (backend vllm-cpp). Partition: ref2va. DiT layout: unpruned. Format: Q4_K_M. This entry is the Ref2VA partition, which takes REFERENCE conditioning (reference images, clips and audio) so the subject or voice carries into the clip. It refuses plain text-to-video and first/last-frame requests: for those use the matching fl2va entry. The DiT is the original time-embedder DiT (~19.9 GB). Render status: verified render (end to end on the vllm.cpp model page). Do NOT use the NVFP4 Ref2VA weights: they render a multicolour patch grid. Q3_K_M of the same DiT is verified BAD and is not offered. The vllm.cpp page records its renders with the DiT expanded to bf16. This entry does not expand it and keeps the quantised weights resident, so a render in that mode is not covered by the page. The weights are one DiT, the Qwen3-VL-32B encoder (~14.6 GB), the video VAE (~10.4 GB), the audio VAE and the tokenizer, plus the two VAE configs that carry the latent statistics. The default canvas is 1344x768 at 124 frames and 24 fps, about 5.2 seconds. Generation is slow: roughly 176 s per denoise step at that canvas on a 20-SM device. Muxing the finished frames needs ffmpeg on the host.

Repository: localaiLicense: other

minimax-h3-ref2va-q4
MiniMax-H3 served by vllm.cpp, LocalAI's own C++ port of vLLM. It generates video AND audio jointly, so a clip comes back as an MP4 with a soundtrack. Ask for speech in the prompt and the model lip-syncs it. Runtime: vllm.cpp (backend vllm-cpp). Partition: ref2va. DiT layout: unpruned. Format: Q4_K_M. This entry is the Ref2VA partition, which takes REFERENCE conditioning (reference images, clips and audio) so the subject or voice carries into the clip. It refuses plain text-to-video and first/last-frame requests: for those use the matching fl2va entry. The DiT is the original time-embedder DiT (~19.9 GB). Render status: verified render (end to end on the vllm.cpp model page). Do NOT use the NVFP4 Ref2VA weights: they render a multicolour patch grid. Q3_K_M of the same DiT is verified BAD and is not offered. The vllm.cpp page records its renders with the DiT expanded to bf16. This entry does not expand it and keeps the quantised weights resident, so a render in that mode is not covered by the page. The weights are one DiT, the Qwen3-VL-32B encoder (~14.6 GB), the video VAE (~10.4 GB), the audio VAE and the tokenizer, plus the two VAE configs that carry the latent statistics. The default canvas is 1344x768 at 124 frames and 24 fps, about 5.2 seconds. Generation is slow: roughly 176 s per denoise step at that canvas on a 20-SM device. Muxing the finished frames needs ffmpeg on the host.

Repository: localaiLicense: other

minimax-h3-fl2va-pruned-q8
MiniMax-H3 served by vllm.cpp, LocalAI's own C++ port of vLLM. It generates video AND audio jointly, so a clip comes back as an MP4 with a soundtrack. Ask for speech in the prompt and the model lip-syncs it. Runtime: vllm.cpp (backend vllm-cpp). Partition: fl2va. DiT layout: pruned. Format: Q8_0. This entry is the FL2VA partition, which serves text-to-video (t2va) and first/last-frame conditioning (fl2va). It refuses reference conditioning: for that use the matching ref2va entry. The DiT is the pruned DiT (AdaLN curve table in place of the per-block modulation projection; about 20B instead of 33B parameters) (~21.4 GB). Render status: loads and renders (vllm.cpp model page, pruned Q8_0 A/B). The vllm.cpp page records its renders with the DiT expanded to bf16. This entry does not expand it and keeps the quantised weights resident, so a render in that mode is not covered by the page. The weights are one DiT, the Qwen3-VL-32B encoder (~14.6 GB), the video VAE (~10.4 GB), the audio VAE and the tokenizer, plus the two VAE configs that carry the latent statistics. The default canvas is 1344x768 at 124 frames and 24 fps, about 5.2 seconds. Generation is slow: roughly 176 s per denoise step at that canvas on a 20-SM device. Muxing the finished frames needs ffmpeg on the host.

Repository: localaiLicense: other

minimax-h3-fl2va-pruned-q6
MiniMax-H3 served by vllm.cpp, LocalAI's own C++ port of vLLM. It generates video AND audio jointly, so a clip comes back as an MP4 with a soundtrack. Ask for speech in the prompt and the model lip-syncs it. Runtime: vllm.cpp (backend vllm-cpp). Partition: fl2va. DiT layout: pruned. Format: Q6_K. This entry is the FL2VA partition, which serves text-to-video (t2va) and first/last-frame conditioning (fl2va). It refuses reference conditioning: for that use the matching ref2va entry. The DiT is the pruned DiT (AdaLN curve table in place of the per-block modulation projection; about 20B instead of 33B parameters) (~16.6 GB). Render status: loads, not rendered. The vllm.cpp model page says the pruned Q6_K file loads through the same path as Q8_0; only Q8_0 has been rendered. The vllm.cpp page records its renders with the DiT expanded to bf16. This entry does not expand it and keeps the quantised weights resident, so a render in that mode is not covered by the page. The weights are one DiT, the Qwen3-VL-32B encoder (~14.6 GB), the video VAE (~10.4 GB), the audio VAE and the tokenizer, plus the two VAE configs that carry the latent statistics. The default canvas is 1344x768 at 124 frames and 24 fps, about 5.2 seconds. Generation is slow: roughly 176 s per denoise step at that canvas on a 20-SM device. Muxing the finished frames needs ffmpeg on the host.

Repository: localaiLicense: other

minimax-h3-fl2va-pruned-q5
MiniMax-H3 served by vllm.cpp, LocalAI's own C++ port of vLLM. It generates video AND audio jointly, so a clip comes back as an MP4 with a soundtrack. Ask for speech in the prompt and the model lip-syncs it. Runtime: vllm.cpp (backend vllm-cpp). Partition: fl2va. DiT layout: pruned. Format: Q5_0. This entry is the FL2VA partition, which serves text-to-video (t2va) and first/last-frame conditioning (fl2va). It refuses reference conditioning: for that use the matching ref2va entry. The DiT is the pruned DiT (AdaLN curve table in place of the per-block modulation projection; about 20B instead of 33B parameters) (~13.9 GB). Render status: loads, not rendered. The vllm.cpp model page says the pruned Q5_0 file loads through the same path as Q8_0; only Q8_0 has been rendered. The vllm.cpp page records its renders with the DiT expanded to bf16. This entry does not expand it and keeps the quantised weights resident, so a render in that mode is not covered by the page. The weights are one DiT, the Qwen3-VL-32B encoder (~14.6 GB), the video VAE (~10.4 GB), the audio VAE and the tokenizer, plus the two VAE configs that carry the latent statistics. The default canvas is 1344x768 at 124 frames and 24 fps, about 5.2 seconds. Generation is slow: roughly 176 s per denoise step at that canvas on a 20-SM device. Muxing the finished frames needs ffmpeg on the host.

Repository: localaiLicense: other

minimax-h3-fl2va-pruned-q4
MiniMax-H3 served by vllm.cpp, LocalAI's own C++ port of vLLM. It generates video AND audio jointly, so a clip comes back as an MP4 with a soundtrack. Ask for speech in the prompt and the model lip-syncs it. Runtime: vllm.cpp (backend vllm-cpp). Partition: fl2va. DiT layout: pruned. Format: Q4_K. This entry is the FL2VA partition, which serves text-to-video (t2va) and first/last-frame conditioning (fl2va). It refuses reference conditioning: for that use the matching ref2va entry. The DiT is the pruned DiT (AdaLN curve table in place of the per-block modulation projection; about 20B instead of 33B parameters) (~11.4 GB). Render status: loads, not rendered. The vllm.cpp model page says the pruned Q4_K file loads through the same path as Q8_0; only Q8_0 has been rendered. The vllm.cpp page records its renders with the DiT expanded to bf16. This entry does not expand it and keeps the quantised weights resident, so a render in that mode is not covered by the page. The weights are one DiT, the Qwen3-VL-32B encoder (~14.6 GB), the video VAE (~10.4 GB), the audio VAE and the tokenizer, plus the two VAE configs that carry the latent statistics. The default canvas is 1344x768 at 124 frames and 24 fps, about 5.2 seconds. Generation is slow: roughly 176 s per denoise step at that canvas on a 20-SM device. Muxing the finished frames needs ffmpeg on the host.

Repository: localaiLicense: other

minimax-h3-fl2va-pruned-q3
MiniMax-H3 served by vllm.cpp, LocalAI's own C++ port of vLLM. It generates video AND audio jointly, so a clip comes back as an MP4 with a soundtrack. Ask for speech in the prompt and the model lip-syncs it. Runtime: vllm.cpp (backend vllm-cpp). Partition: fl2va. DiT layout: pruned. Format: Q3_K. This entry is the FL2VA partition, which serves text-to-video (t2va) and first/last-frame conditioning (fl2va). It refuses reference conditioning: for that use the matching ref2va entry. The DiT is the pruned DiT (AdaLN curve table in place of the per-block modulation projection; about 20B instead of 33B parameters) (~8.8 GB). Render status: loads, not rendered. The vllm.cpp model page says the pruned Q3_K file loads through the same path as Q8_0; only Q8_0 has been rendered. The vllm.cpp page records its renders with the DiT expanded to bf16. This entry does not expand it and keeps the quantised weights resident, so a render in that mode is not covered by the page. The weights are one DiT, the Qwen3-VL-32B encoder (~14.6 GB), the video VAE (~10.4 GB), the audio VAE and the tokenizer, plus the two VAE configs that carry the latent statistics. The default canvas is 1344x768 at 124 frames and 24 fps, about 5.2 seconds. Generation is slow: roughly 176 s per denoise step at that canvas on a 20-SM device. Muxing the finished frames needs ffmpeg on the host.

Repository: localaiLicense: other

minimax-h3-fl2va-pruned-q2
MiniMax-H3 served by vllm.cpp, LocalAI's own C++ port of vLLM. It generates video AND audio jointly, so a clip comes back as an MP4 with a soundtrack. Ask for speech in the prompt and the model lip-syncs it. Runtime: vllm.cpp (backend vllm-cpp). Partition: fl2va. DiT layout: pruned. Format: Q2_K. This entry is the FL2VA partition, which serves text-to-video (t2va) and first/last-frame conditioning (fl2va). It refuses reference conditioning: for that use the matching ref2va entry. The DiT is the pruned DiT (AdaLN curve table in place of the per-block modulation projection; about 20B instead of 33B parameters) (~6.7 GB). Render status: loads, not rendered. The vllm.cpp model page says the pruned Q2_K file loads through the same path as Q8_0; only Q8_0 has been rendered. The vllm.cpp page records its renders with the DiT expanded to bf16. This entry does not expand it and keeps the quantised weights resident, so a render in that mode is not covered by the page. The weights are one DiT, the Qwen3-VL-32B encoder (~14.6 GB), the video VAE (~10.4 GB), the audio VAE and the tokenizer, plus the two VAE configs that carry the latent statistics. The default canvas is 1344x768 at 124 frames and 24 fps, about 5.2 seconds. Generation is slow: roughly 176 s per denoise step at that canvas on a 20-SM device. Muxing the finished frames needs ffmpeg on the host.

Repository: localaiLicense: other

minimax-h3-ref2va-pruned-q8
MiniMax-H3 served by vllm.cpp, LocalAI's own C++ port of vLLM. It generates video AND audio jointly, so a clip comes back as an MP4 with a soundtrack. Ask for speech in the prompt and the model lip-syncs it. Runtime: vllm.cpp (backend vllm-cpp). Partition: ref2va. DiT layout: pruned. Format: Q8_0. This entry is the Ref2VA partition, which takes REFERENCE conditioning (reference images, clips and audio) so the subject or voice carries into the clip. It refuses plain text-to-video and first/last-frame requests: for those use the matching fl2va entry. The DiT is the pruned DiT (AdaLN curve table in place of the per-block modulation projection; about 20B instead of 33B parameters) (~21.4 GB). Render status: loads and renders (vllm.cpp model page, pruned Q8_0 A/B). The vllm.cpp page records its renders with the DiT expanded to bf16. This entry does not expand it and keeps the quantised weights resident, so a render in that mode is not covered by the page. The weights are one DiT, the Qwen3-VL-32B encoder (~14.6 GB), the video VAE (~10.4 GB), the audio VAE and the tokenizer, plus the two VAE configs that carry the latent statistics. The default canvas is 1344x768 at 124 frames and 24 fps, about 5.2 seconds. Generation is slow: roughly 176 s per denoise step at that canvas on a 20-SM device. Muxing the finished frames needs ffmpeg on the host.

Repository: localaiLicense: other

minimax-h3-ref2va-pruned-q6
MiniMax-H3 served by vllm.cpp, LocalAI's own C++ port of vLLM. It generates video AND audio jointly, so a clip comes back as an MP4 with a soundtrack. Ask for speech in the prompt and the model lip-syncs it. Runtime: vllm.cpp (backend vllm-cpp). Partition: ref2va. DiT layout: pruned. Format: Q6_K. This entry is the Ref2VA partition, which takes REFERENCE conditioning (reference images, clips and audio) so the subject or voice carries into the clip. It refuses plain text-to-video and first/last-frame requests: for those use the matching fl2va entry. The DiT is the pruned DiT (AdaLN curve table in place of the per-block modulation projection; about 20B instead of 33B parameters) (~16.6 GB). Render status: loads, not rendered. The vllm.cpp model page says the pruned Q6_K file loads through the same path as Q8_0; only Q8_0 has been rendered. The vllm.cpp page records its renders with the DiT expanded to bf16. This entry does not expand it and keeps the quantised weights resident, so a render in that mode is not covered by the page. The weights are one DiT, the Qwen3-VL-32B encoder (~14.6 GB), the video VAE (~10.4 GB), the audio VAE and the tokenizer, plus the two VAE configs that carry the latent statistics. The default canvas is 1344x768 at 124 frames and 24 fps, about 5.2 seconds. Generation is slow: roughly 176 s per denoise step at that canvas on a 20-SM device. Muxing the finished frames needs ffmpeg on the host.

Repository: localaiLicense: other

minimax-h3-ref2va-pruned-q5
MiniMax-H3 served by vllm.cpp, LocalAI's own C++ port of vLLM. It generates video AND audio jointly, so a clip comes back as an MP4 with a soundtrack. Ask for speech in the prompt and the model lip-syncs it. Runtime: vllm.cpp (backend vllm-cpp). Partition: ref2va. DiT layout: pruned. Format: Q5_0. This entry is the Ref2VA partition, which takes REFERENCE conditioning (reference images, clips and audio) so the subject or voice carries into the clip. It refuses plain text-to-video and first/last-frame requests: for those use the matching fl2va entry. The DiT is the pruned DiT (AdaLN curve table in place of the per-block modulation projection; about 20B instead of 33B parameters) (~13.9 GB). Render status: loads, not rendered. The vllm.cpp model page says the pruned Q5_0 file loads through the same path as Q8_0; only Q8_0 has been rendered. The vllm.cpp page records its renders with the DiT expanded to bf16. This entry does not expand it and keeps the quantised weights resident, so a render in that mode is not covered by the page. The weights are one DiT, the Qwen3-VL-32B encoder (~14.6 GB), the video VAE (~10.4 GB), the audio VAE and the tokenizer, plus the two VAE configs that carry the latent statistics. The default canvas is 1344x768 at 124 frames and 24 fps, about 5.2 seconds. Generation is slow: roughly 176 s per denoise step at that canvas on a 20-SM device. Muxing the finished frames needs ffmpeg on the host.

Repository: localaiLicense: other

Page 1