Step GGUF models

75 GGUF models in the Step family, quantized by 49 uploaders. Sizes run from 1.72B to 601B parameters. The longest trained context is 1024K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
ST
Step-3.7-Flash
Step · unsloth
Params197B
Context256K
Q4_K_M122.1 GB
Vision
ST
Step 3.5 Flash
Step · ggml-org
Params197B
Context256K
Smallest118.7 GB
GGUF
ST
Step-5-Preview-BF16
Step · L-Alchemyst
Params601B
Context1024K
Smallest248.8 GB
ReasoningTool useVision
ST
Step 3.7 Flash
Step · stepfun-ai
Params197B
Context—
Smallest0.5 GB
GGUF
ST
Step3 VL 10B
Step · seanbailey518
Params8.19B
Context64K
Q4_K_M5.0 GB
Vision
ST
Step 3.7 Flash AEON Ultimate Abliterated
Step · Vegss
Params197B
Context256K
Smallest48.4 GB
ReasoningTool useVision
ST
Step 5 Preview
Step · smalinin
Params601B
Context1024K
Smallest1.2 GB
GGUF
ST
Step 3.5 Flash REAP 149B A11B i1
Step · mradermacher
Params149B
Context256K
Q4_K_M89.9 GB
GGUF
ST
Step3 VL 10B Base
Step · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
Vision
ST
Step 3.5 Flash
Step · bartowski
Params197B
Context256K
Q4_K_M119.9 GB
GGUF
ST
Step-3.7
Step · mudler
Params197B
Context256K
Smallest72.9 GB
Vision
ST
Step 3.5 Flash REAP 121B A11B i1
Step · mradermacher
Params121B
Context256K
Q4_K_M72.8 GB
ReasoningTool use
ST
Step 3.5 Flash APEX
Step · mudler
Params197B
Context256K
Smallest76.5 GB
GGUF
ST
Step 3.7 Flash
Step · bartowski
Params199B
Context256K
Q4_K_M121.6 GB
ReasoningTool useVision
ST
Step 3.5 Flash
Step · mradermacher
Params197B
Context256K
Q4_K_M118.6 GB
ReasoningTool use
ST
Step 3.5 Flash Ablitirated
Step · mradermacher
Params197B
Context256K
Q4_K_M118.6 GB
ReasoningTool use
ST
Step 3.5 Flash REAP 128B A11B
Step · mradermacher
Params121B
Context256K
Q4_K_M72.8 GB
CodingReasoningTool use
ST
Step 3.5 Flash GGUF Q4 K S
Step · stepfun-ai
Params197B
Context256K
Smallest111.5 GB
CodingReasoningTool use
ST
Cerebras Step 3.5 Flash REAP 149B A11B
Step · wimmmm
Params149B
Context256K
Smallest0.4 GB
GGUF
ST
Step 3.7 Flash ARA Heretic
Step · PeterCxy
Params197B
Context256K
Smallest105.0 GB
ReasoningTool useVision
ST
Step 3.5 Flash REAP 128B A11B
Step · mradermacher
Params121B
Context256K
Q4_K_M72.8 GB
CodingReasoningTool use
ST
Step3 VL 10B
Step · JamePeng2023
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool useVision
ST
Step 3.5 Flash
Step · mradermacher
Params197B
Context256K
Q4_K_M118.6 GB
ReasoningTool use
ST
Step 3.5 Flash PRISM
Step · Ex0bit
Params197B
Context256K
Smallest64.0 GB
ReasoningTool use
ST
rm_1014_20K_70K_step_400
Step · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
ST
Step3 VL 10B Base
Step · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
Vision
ST
Step 3.5 Flash Ablitirated
Step · mradermacher
Params197B
Context256K
Q4_K_M118.6 GB
ReasoningTool use
ST
Step-3.7-Flash
Step · vultr
Params197B
Context256K
Q4_K_M130.4 GB
ReasoningTool useVision
ST
rm_1014_70K_step_600_lr_1e6
Step · RichardErkhov
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
ST
cerebras/Step-3.5-Flash-REAP-149B-A11B
Step · mradermacher
Params149B
Context256K
Q4_K_M89.9 GB
ReasoningTool use

About the Step GGUF models

Step is represented on ggufmodels.com by 75 GGUF models, quantized by 49 uploaders on Hugging Face. The most downloaded are Step-3.7-Flash, Step 3.5 Flash and Step-5-Preview-BF16. Parameter counts run from 1.72B to 601B, and the longest trained context window is 1024K tokens.

A Q4_K_M file of a Step model is between 1.1 to 130.4 GB, which is the quant most people start with. Most files come from mradermacher (13), stepfun-ai (3) and notSnix (3). The quants you will meet most often are Q4_K_M (38), Q8_0 (33), Q6_K (32) and IQ4_XS (32), where the number is how many models offer that quant.

Frequently asked questions

Which Step GGUF should I download?

The most downloaded Step GGUF here is Step-3.7-Flash. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Step model need?

Q4_K_M files of Step models on this site range from 1.1 to 130.4 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Step GGUF files come from?

The most common quantizers here are mradermacher, stepfun-ai and notSnix. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing