No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from stepfun-ai/Step-3.7-Flash-GGUF
All models by stepfun-ai →[ModelPage]: https://static.stepfun.com/blog/step-3.7-flash/
GGUF quantizations of stepfun-ai/Step-3.7-Flash.
Step-3.7-Flash is a 198B-parameter sparse Mixture-of-Experts vision-language model from StepFun-ai, activating ~11B parameters per token for up to 400 t/s throughput. It pairs a 196B-parameter language backbone with a 1.8B-parameter vision encoder for native image understanding, supports a 256K context window, and offers three selectable reasoning levels (low / medium / high) to balance speed, cost, and depth. Built for agentic workloads — tool calling, multi-step reasoning, code, and math — with native multilingual coverage.
A separate mmproj projector ships alongside the language quants for multimodal inference. With 128 GB of unified memory (Mac Studio, DGX Spark, Ryzen AI Max+ 395, etc.), you can privately host Step-3.7-Flash: Q4 quants and below run at full 256K context with high precision.
Build llama.cpp and run:
For full CLI / server options, see the llama.cpp README.
Step-3.7-flash-Q4_K_S
Step-3.7-flash-IQ4_XS
Step-3.7-flash-Q3_K_L
Step-3.7-flash-Q4_K_S
Step-3.7-flash-IQ4_XS
Step-3.7-flash-Q3_K_L
Step-3.7-flash-Q4_K_S
Step-3.7-flash-IQ4_XS
Step-3.7-flash-Q3_K_L
This release stands on the work of the following authors and communities:
calibration_datav5,
the community-standard imatrix calibration anchor used by countless GGUF releases.
Used for calibration purposes only; no license has been verified for this resource.imatrix-calibration
dataset (MIT), providing multilingual / code / math splits that form the backbone of this release's domain balancehermes-function-calling-v1
(Apache-2.0), used for agent / tool-call calibration coverageThe GGUF quantization files in this repository are derivative works of
stepfun-ai/Step-3.7-Flash
and are released under the same Apache 2.0 license.
All calibration datasets retain their original licenses and are used strictly for quantization calibration purposes only.
# 1. Clone and buildgit clone https://github.com/stepfun-ai/llama.cpp.gitcd llama.cppgit checkout -b step3.7 origin/step3.7cmake -B build -DLLAMA_BUILD_TOOLS=ON -DLLAMA_BUILD_SERVER=ONcmake --build build --config Release -j$(nproc)
# 2. Test performance (benchmark)./build/bin/llama-batched-bench \ -m Step-3.7-flash-Q4_K_S.gguf \ -c 32768 -b 2048 -ub 2048 \ -npp 0,2048,8192,16384,32768 -ntg 128 -npl 1
# 3. Text-only inference./build/bin/llama-cli \ -m Step-3.7-flash-Q4_K_S.gguf \ -c 32768 -ngl 99 -fa on \ -p "Write a Python function to compute the n-th Fibonacci number."
# 4. With vision (image + text)./build/bin/llama-mtmd-cli \ -m Step-3.7-flash-Q4_K_S.gguf \ --mmproj mmproj-Step-3.7-flash-f16.gguf \ -c 32768 -ngl 99 -fa on \ --image path/to/image.jpg \ -p "Describe this image."
# 5. OpenAI-compatible server (text + vision)./build/bin/llama-server \ -m Step-3.7-flash-Q4_K_S.gguf \ --mmproj mmproj-Step-3.7-flash-f16.gguf \ -c 32768 -ngl 99 -fa on \ --host 0.0.0.0 --port 8080./llama-batched-bench -m Step-3.7-flash-Q4_K_S.gguf -c 262150 -b 2048 -ub 1024 -npp 0,2048,8192,16384,32768,65536,131072,262144 -ntg 128 -npl 1./llama-batched-bench -m Step-3.7-flash-IQ4_XS.gguf -c 262150 -b 2048 -ub 1024 -npp 0,2048,8192,16384,32768,65536,131072,262144 -ntg 128 -npl 1./llama-batched-bench -m Step-3.7-flash-Q3_K_L.gguf -c 262272 -b 2048 -ub 1024 -npp 0,2048,8192,16384,32768,65536,131072,262144 -ntg 128 -npl 1./llama-batched-bench -m Step-3.7-flash-Q4_K_S.gguf -c 131300 -b 2048 -ub 1024 -npp 0,2048,8192,16384,32768,65536,131072 -ntg 128 -npl 1./llama-batched-bench -m Step-3.7-flash-IQ4_XS.gguf -c 262272 -b 2048 -ub 1024 -npp 0,2048,8192,16384,32768,65536,131072,262144 -ntg 128 -npl 1./llama-batched-bench -m Step-3.7-flash-Q3_K_L.gguf -c 262272 -b 2048 -ub 1024 -npp 0,2048,8192,16384,32768,65536,131072,262144 -ntg 128 -npl 1llama-batched-bench.exe -m Step-3.7-flash-Q4_K_S.gguf -c 65664 -b 2048 -ub 1024 -npp 0,2048,8192,16384,32768,65536 -ntg 128 -npl 1./llama-batched-bench -m Step-3.7-flash-IQ4_XS.gguf -c 65664 -b 2048 -ub 1024 -npp 0,2048,8192,16384,32768,65536 -ntg 128 -npl 1./llama-batched-bench -m Step-3.7-flash-Q3_K_L.gguf -c 262272 -b 2048 -ub 1024 -ctk q8_0 -ctv q8_0 -npp 0,2048,8192,16384,32768,65536,131072,262144 -ntg 128 -npl 1