deepseek-ai/DeepSeek-V4-Flash
95 derivatives checked
- antirez/deepseek-v4-gguf: Not comparable yet
- sgl-project/DeepSeek-V4-Flash-FP8: Different architecture
- huihui-ai/Huihui-DeepSeek-V4-Flash-abliterated-ds4-GGUF: Not comparable yet
- nvidia/DeepSeek-V4-Flash-NVFP4: Quantization
- unsloth/DeepSeek-V4-Flash-GGUF: Not comparable yet
- jedisct1/DeepSeek-V4-Flash-imatrix-aligned: Not comparable yet
- fraserprice/DeepSeek-V4-Flash-DSpark: Partial fine-tune
- amd/DeepSeek-V4-Flash-MXFP4: Quantization
- cyberneurova/CyberNeurova-DeepSeek-V4-Flash-abliterated-GGUF: Not comparable yet
- mlx-community/DeepSeek-V4-Flash: Quantization
- nvidia/DeepSeek-V4-Flash-nvfp4-DSpark: Quantization
- bleysg/DeepSeek-V4-Flash-DSpark-drafter-GGUF: Not comparable yet
- teamblobfish/DeepSeek-V4-Flash-GGUF: Not comparable yet
- RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8: Quantization
- ggml-org/DeepSeek-V4-Flash-GGUF: Not comparable yet
- sleepyeldrazi/DeepSeek-v4-Flash-REAP-K128-NVFP4: Not comparable yet
- mlx-community/deepseek-ai-DeepSeek-V4-Flash-8bit: Quantization
- bullerwins/DeepSeek-V4-Flash-GGUF: Not comparable yet
- TheDrainFlorist/DeepSeek-V4-Flash-VQ-3.2bpw: Quantization
- tarruda/DeepSeek-V4-Flash-GGUF: Not comparable yet
- audreyt/CyberNeurova-DeepSeek-V4-Flash-abliterated-GGUF: Not comparable yet
- inferencerlabs/DeepSeek-V4-Flash-MLX-Q2i: Different architecture
- Intel/DeepSeek-V4-Flash-W4A16-AutoRound: Quantization
- YanissAmz/DeepSeek-V4-Flash-DSpark-draft-GGUF: Not comparable yet
- andreaborio/DeepSeek-V4-Flash-Hebrus-GGUF: Not comparable yet
- zenlm/zen5-pro-gguf: Not comparable yet
- canada-quant/DeepSeek-V4-Flash-W4A16-FP8-MTP: Quantization
- kshitijthakkar/deepseek-v4-mini-1B-from-flash: Different architecture
- ddh0/DeepSeek-V4-Flash-GGUF: Not comparable yet
- Thump604/DeepSeek-V4-Flash-MLX-Q2-mixed-gs128-affine: Quantization
70 other repos hold byte-for-byte identical weight files.