Views
No views yet
| Property | Value |
|---|---|
| Base Model | z-lab/Kimi-K2.5-DFlash |
| Architecture | DFlashDraftModel |
| Format | GGUF v3 (float32 + quantized) |
| Original Dtype | bfloat16 (converted to float32 for GGUF compatibility) |
| Hidden Size | 7,168 |
| Layers | 6 |
| Attention Heads | 64 (Q) / 8 (KV) |
| Intermediate Size | 18,432 |
| Vocab Size | 163,840 |
| Max Position Embeddings | 262,144 |
| RoPE Type | YaRN (factor=64, theta=50k) |
| Tensor Count | 69 |
| File | Size | Quantization | Description |
|---|---|---|---|
Kimi-K2.5-DFlash.gguf | ~13.9 GB | F32 (float32) | Full precision base model |
Kimi-K2.5-DFlash-Q8_0.gguf | ~3.5 GB | Q8_0 | 4x smaller, high quality |
Kimi-K2.5-DFlash-Q5_0.gguf | ~2.3 GB | Q5_0 | 6x smaller, good quality |
Kimi-K2.5-DFlash-Q4_0.gguf | ~1.9 GB | Q4_0 | 7x smaller, fastest inference |
oxidize --model /path/to/Kimi-K2.5-DFlash-Q4_0.gguf --speculative-config ...dflash-draft architecture. Standard llama.cpp does not natively support DFlashDraftModel inference. Use oxidize or wait for upstream support.z-lab/Kimi-K2.5-DFlash (SafeTensors, bfloat16)gguf library + safetensors.torchgguf.quants.quantize() with GGMLQuantizationTypelayers.N.self_attn.q_proj.weight) → oxidize GGUF names (blk.N.attn_q.weight)general.architecture=dflash-draft and all model hyperparameterslm_head or embed_tokens weights: DFlash draft models reuse the target model's token embeddingsmoonshotai/Kimi-K2.6) for speculative decodingz-lab/Kimi-K2.5-DFlash model.