Add Step 3.7 Flash MTP draft GGUFs

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Step-3.7-Flash-MTP-BF16.gguf filter=lfs diff=lfs merge=lfs -text
+Step-3.7-Flash-MTP-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Step-3.7-Flash-MTP-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,87 @@
+---
+license: apache-2.0
+base_model:
+- stepfun-ai/Step-3.7-Flash
+library_name: gguf
+language:
+- en
+tags:
+- gguf
+- llama.cpp
+- mtp
+- draft-model
+- speculative-decoding
+- q4_k_m
+- q8_0
+- bf16
+- stepfun
+---
+
+# Step 3.7 Flash MTP Draft GGUFs
+
+These are companion MTP draft GGUFs for speculative decoding. They are not standalone chat models.
+
+Use them with the full model repo:
+
+[notSnix/Step-3.7-Flash-Q4_K_M-GGUF](https://huggingface.co/notSnix/Step-3.7-Flash-Q4_K_M-GGUF)
+
+The draft GGUF is passed with `--model-draft`; the full model is passed with `--model`.
+
+## Files
+
+| File | Size | SHA256 | Purpose |
+|---|---:|---|---|
+| `Step-3.7-Flash-MTP-Q8_0.gguf` | 3.5 GB | `017de8990140621b5b4af431448f20873fbf0b052f6c50d2afac15f45802a98d` | Recommended MTP draft |
+| `Step-3.7-Flash-MTP-Q4_K_M.gguf` | 2.0 GB | `44118cfe64f45b38127ad6fb626e16bd94ee5a827cb34aa83d9e6df3450aebaf` | Smaller MTP draft |
+| `Step-3.7-Flash-MTP-BF16.gguf` | 6.5 GB | `fd811c81d14c786d314d8006655bba61971059abcfdfb6109ce83fd768f8b289` | Experimental BF16 MTP draft |
+
+## Runtime
+
+Current llama.cpp `main` supports Step MTP-tail draft loading natively. This was smoke-tested with clean llama.cpp commit `d545a2a993849fcf3b752d85ae256fc9d6a9de79`.
+
+```bash
+git clone https://github.com/ggml-org/llama.cpp
+cd llama.cpp
+cmake -B build-cuda -DGGML_CUDA=ON
+cmake --build build-cuda --config Release -j
+```
+
+## Usage
+
+```bash
+llama-server \
+  --model Step-3.7-Flash-Q4_K_M.gguf \
+  --model-draft Step-3.7-Flash-MTP-Q8_0.gguf \
+  --host 0.0.0.0 \
+  --port 8000 \
+  --ctx-size 262144 \
+  --n-gpu-layers all \
+  --split-mode layer \
+  --parallel 1 \
+  --reasoning on \
+  --reasoning-format deepseek \
+  --spec-type draft-mtp \
+  --spec-draft-n-max 2 \
+  --spec-draft-p-min 0.60
+```
+
+## Which Draft Should I Use?
+
+Use `Step-3.7-Flash-MTP-Q8_0.gguf` first. It was the best local default in testing.
+
+Use `Step-3.7-Flash-MTP-Q4_K_M.gguf` if you want the smaller draft file.
+
+Use `Step-3.7-Flash-MTP-BF16.gguf` for experimentation.
+
+## Checksums
+
+```bash
+sha256sum -c SHA256SUMS
+```
+
+## Notes
+
+- These files intentionally keep the upstream Step MTP tail-layer numbering (`blk.45`, `blk.46`, `blk.47`).
+- They are companion speculative-decoding draft GGUFs, not full-model quants.
+- The full Q4_K_M model is hosted separately so Hugging Face's GGUF widget does not display draft files as tiny full-model quantizations.
+- This is a community GGUF conversion of the upstream Apache-2.0 model, not an official StepFun release.

SHA256SUMS

@@ -0,0 +1,3 @@
+017de8990140621b5b4af431448f20873fbf0b052f6c50d2afac15f45802a98d  Step-3.7-Flash-MTP-Q8_0.gguf
+44118cfe64f45b38127ad6fb626e16bd94ee5a827cb34aa83d9e6df3450aebaf  Step-3.7-Flash-MTP-Q4_K_M.gguf
+fd811c81d14c786d314d8006655bba61971059abcfdfb6109ce83fd768f8b289  Step-3.7-Flash-MTP-BF16.gguf

Step-3.7-Flash-MTP-BF16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd811c81d14c786d314d8006655bba61971059abcfdfb6109ce83fd768f8b289
+size 6973539520

Step-3.7-Flash-MTP-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44118cfe64f45b38127ad6fb626e16bd94ee5a827cb34aa83d9e6df3450aebaf
+size 2138133696

Step-3.7-Flash-MTP-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:017de8990140621b5b4af431448f20873fbf0b052f6c50d2afac15f45802a98d
+size 3707266240