Filter by type:
Filter by tags:
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-tts-llamacpp
Qwen3-TTS 1.7B Base served by the llama.cpp backend, using upstream's own
GGUF conversion. Runs on the full llama-cpp accelerator matrix (CUDA, ROCm,
SYCL, Vulkan, Metal). Streaming output and zero-shot voice cloning: set
`voice` to a reference clip or a saved Voice Library profile, which is
required since the Base checkpoint has no built-in speaker. 24kHz mono,
10 languages. Q8_0 backbone (~1.8 GB) plus a Q8_0 projector.
Repository: localaiLicense: apache-2.0
kimodo-soma-rp
Kimodo SOMA RP v1.1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic Q8_0 Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
Repository: localai
kimodo-soma-rp-q6_k
Kimodo SOMA RP v1.1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic Q6_K Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
Repository: localai
kimodo-soma-rp-q5_k
Kimodo SOMA RP v1.1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic Q5_K Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
Repository: localai
kimodo-soma-rp-q4_k_m
Kimodo SOMA RP v1.1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic Q4_K_M Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
Repository: localai
kimodo-soma-rp-q4_k
Kimodo SOMA RP v1.1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic Q4_K Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
Repository: localai
kimodo-soma-rp-bf16
Kimodo SOMA RP v1.1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic BF16 Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
BF16 needs substantial memory with all layers resident; use text_layer_chunk:8 on smaller GPUs.
Repository: localai
kimodo-soma-seed
Kimodo SOMA SEED v1.1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic Q8_0 Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
Repository: localai
kimodo-soma-seed-q6_k
Kimodo SOMA SEED v1.1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic Q6_K Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
Repository: localai
kimodo-soma-seed-q5_k
Kimodo SOMA SEED v1.1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic Q5_K Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
Repository: localai
kimodo-soma-seed-q4_k_m
Kimodo SOMA SEED v1.1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic Q4_K_M Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
Repository: localai
kimodo-soma-seed-q4_k
Kimodo SOMA SEED v1.1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic Q4_K Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
Repository: localai
kimodo-soma-seed-bf16
Kimodo SOMA SEED v1.1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic BF16 Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
BF16 needs substantial memory with all layers resident; use text_layer_chunk:8 on smaller GPUs.
Repository: localai
kimodo-g1-rp
Kimodo G1 RP v1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic Q8_0 Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
Repository: localai
kimodo-g1-rp-q6_k
Kimodo G1 RP v1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic Q6_K Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
Repository: localai
kimodo-g1-rp-q5_k
Kimodo G1 RP v1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic Q5_K Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
Repository: localai
kimodo-g1-rp-q4_k_m
Kimodo G1 RP v1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic Q4_K_M Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
Repository: localai
kimodo-g1-rp-q4_k
Kimodo G1 RP v1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic Q4_K Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
Repository: localai
kimodo-g1-rp-bf16
Kimodo G1 RP v1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic BF16 Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
BF16 needs substantial memory with all layers resident; use text_layer_chunk:8 on smaller GPUs.
Repository: localai
kimodo-g1-seed
Kimodo G1 SEED v1 text-to-motion on CPU or Vulkan, with F32 motion weights
and the shared monolithic Q8_0 Llama-3/LLM2Vec text encoder.
Exports an animated skeleton GLB without a mesh or skin. Motion and text
weights retain their respective NVIDIA Open Model License and Llama 3 terms.
Repository: localai
Page 1