scratch / llms

69.8 GB

Ctrl+K

2 contributors

History: 42 commits

Bartosz Hanc

Add Gemma 4 Omni E2B MLX int4 model

cb2e07e 29 days ago

bielik_v3_0_1_5b_xnnpack_8da4w.pte

937 MB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago
gemma4_e2b_mlx_int4.pte

2.53 GB
xet

Upload llms/gemma4_e2b_mlx_int4.pte with huggingface_hub 30 days ago
gemma_4_e2b_vulkan_8da4w.pte

2.99 GB
xet

Upload llms/gemma_4_e2b_vulkan_8da4w.pte with huggingface_hub 30 days ago
gemma_4_e2b_xnnpack_8da4w.pte

2.81 GB
xet

Add Gemma 4 E2B XNNPACK 8da4w re-exported for the TypeScript runner (text-only, ctx 4096, seq 1024, fp32 [1, vocab] logits, get_model_schema) 30 days ago
gemma_4_omni_e2b_mlx_int4.pte

2.73 GB
xet

Add Gemma 4 Omni E2B MLX int4 model 29 days ago
hammer_2_1_0_5b_mlx_int4.pte

534 MB
xet

Re-export hammer_2_1_0_5b_mlx_int4.pte with the SWM ExecuTorch fork (ctx 16384, seq 2048, fp32 logits, get_model_schema) 30 days ago
hammer_2_1_0_5b_xnnpack_8da4w.pte

432 MB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago
hammer_2_1_1_5b_mlx_int4.pte

1.29 GB
xet

Re-export hammer_2_1_1_5b_mlx_int4.pte with the SWM ExecuTorch fork (ctx 16384, seq 2048, fp32 logits, get_model_schema) 30 days ago
hammer_2_1_1_5b_xnnpack_8da4w.pte

1.16 GB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago
hammer_2_1_3b_mlx_int4.pte

2.26 GB
xet

Re-export hammer_2_1_3b_mlx_int4.pte with the SWM ExecuTorch fork (ctx 8192, seq 2048, fp32 logits, get_model_schema) 30 days ago
hammer_2_1_3b_xnnpack_8da4w.pte

2.07 GB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago
lfm_2_5_1_2b_mlx_int4.pte

891 MB
xet

Re-export lfm_2_5_1_2b_mlx_int4.pte with the SWM ExecuTorch fork (ctx 16384, seq 65, fp32 logits, get_model_schema) 30 days ago
lfm_2_5_1_2b_xnnpack_8da4w.pte

810 MB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago
lfm_2_5_350m_mlx_int4.pte

323 MB
xet

Re-export lfm_2_5_350m_mlx_int4.pte with the SWM ExecuTorch fork (ctx 16384, seq 65, fp32 logits, get_model_schema) 30 days ago
lfm_2_5_350m_xnnpack_8da4w.pte

292 MB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago
lfm_2_5_vl_1_6b_mlx_int4.pte

2.37 GB
xet

Add LFM 2.5 VL 1.6B MLX int4 re-exported with the SWM ExecuTorch fork (fp32 method boundaries, get_model_schema) 30 days ago
lfm_2_5_vl_1_6b_mlx_int8.pte

2.96 GB
xet

Add LFM 2.5 VL 1.6B MLX int8 re-exported with the SWM ExecuTorch fork (fp32 method boundaries, get_model_schema) 30 days ago
lfm_2_5_vl_1_6b_vulkan_8da4w.pte

2.47 GB
xet

Add LFM 2.5 VL 1.6B Vulkan 8da4w re-exported with the SWM ExecuTorch 1.4.1 fork (get_model_schema) 30 days ago
lfm_2_5_vl_1_6b_xnnpack_8da4w.pte

2.47 GB
xet

Add lfm_2_5_vl XNNPACK models with get_model_schema (2k context) about 1 month ago
lfm_2_5_vl_450m_mlx_int4.pte

582 MB
xet

Add LFM 2.5 VL 450M MLX int4 re-exported with the SWM ExecuTorch fork (fp32 method boundaries, get_model_schema) 30 days ago
lfm_2_5_vl_450m_vulkan_8da4w.pte

622 MB
xet

Add LFM 2.5 VL 450M Vulkan 8da4w re-exported with the SWM ExecuTorch 1.4.1 fork (get_model_schema) 30 days ago
lfm_2_5_vl_450m_xnnpack_8da4w.pte

649 MB
xet

Add lfm_2_5_vl XNNPACK models with get_model_schema (2k context) about 1 month ago
llama_3_2_1b_mlx_int4.pte

1.18 GB
xet

Re-export llama_3_2_1b_mlx_int4.pte with the SWM ExecuTorch fork (ctx 16384, seq 2048, fp32 logits, get_model_schema) 30 days ago
llama_3_2_1b_xnnpack_spinquant.pte

1.08 GB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago
llama_3_2_3b_mlx_int4.pte

2.5 GB
xet

Re-export llama_3_2_3b_mlx_int4.pte with the SWM ExecuTorch fork (ctx 4096, seq 2048, fp32 logits, get_model_schema) 30 days ago
llama_3_2_3b_xnnpack_spinquant.pte

2.38 GB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago
phi_4_mini_mlx_int4.pte

3.27 GB
xet

Re-export phi_4_mini_mlx_int4.pte with the SWM ExecuTorch fork (ctx 4096, seq 2048, fp32 logits, get_model_schema) 30 days ago
phi_4_mini_xnnpack_8da4w.pte

2.82 GB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago
qwen_2_5_0_5b_mlx_int4.pte

535 MB
xet

Re-export qwen_2_5_0_5b_mlx_int4.pte with the SWM ExecuTorch fork (ctx 16384, seq 2048, fp32 logits, get_model_schema) 30 days ago
qwen_2_5_0_5b_xnnpack_8da4w.pte

432 MB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago
qwen_2_5_1_5b_mlx_int4.pte

1.29 GB
xet

Re-export qwen_2_5_1_5b_mlx_int4.pte with the SWM ExecuTorch fork (ctx 16384, seq 2048, fp32 logits, get_model_schema) 30 days ago
qwen_2_5_1_5b_xnnpack_8da4w.pte

1.17 GB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago
qwen_2_5_3b_mlx_int4.pte

2.26 GB
xet

Re-export qwen_2_5_3b_mlx_int4.pte with the SWM ExecuTorch fork (ctx 8192, seq 2048, fp32 logits, get_model_schema) 30 days ago
qwen_2_5_3b_xnnpack_8da4w.pte

2.1 GB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago
qwen_3_0_6b_mlx_int4.pte

628 MB
xet

Re-export qwen_3_0_6b_mlx_int4.pte with the SWM ExecuTorch fork (ctx 8192, seq 2048, fp32 logits, get_model_schema) 30 days ago
qwen_3_0_6b_xnnpack_8da4w.pte

518 MB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago
qwen_3_1_7b_mlx_int4.pte

1.54 GB
xet

Re-export qwen_3_1_7b_mlx_int4.pte with the SWM ExecuTorch fork (ctx 4096, seq 2048, fp32 logits, get_model_schema) 30 days ago
qwen_3_1_7b_xnnpack_8da4w.pte

1.31 GB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago
qwen_3_4b_mlx_int4.pte

2.92 GB
xet

Re-export qwen_3_4b_mlx_int4.pte with the SWM ExecuTorch fork (ctx 4096, seq 2048, fp32 logits, get_model_schema) 30 days ago
qwen_3_4b_xnnpack_8da4w.pte

2.69 GB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago
smollm2_135m_mlx_int8.pte

196 MB
xet

Add SmolLM2 135M/360M MLX int8 re-exported with the SWM ExecuTorch fork (16k context, fp32 logits, get_model_schema) 30 days ago
smollm2_135m_xnnpack_8da8w.pte

173 MB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago
smollm2_1_7b_mlx_int8.pte

1.97 GB
xet

Add SmolLM2 1.7B MLX int8 re-exported with the SWM ExecuTorch fork (2k context, fp32 logits, get_model_schema) 30 days ago
smollm2_1_7b_xnnpack_8da8w.pte

1.82 GB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago
smollm2_360m_mlx_int8.pte

468 MB
xet

Add SmolLM2 135M/360M MLX int8 re-exported with the SWM ExecuTorch fork (16k context, fp32 logits, get_model_schema) 30 days ago
smollm2_360m_xnnpack_8da8w.pte

420 MB
xet

Rename LLM exports to their canonical react-native-executorch file names 30 days ago