What are the hardware requirements for Step 3.5 Flash GGUF Q4 K S?

Step 3.5 Flash GGUF Q4 K S requires approximately 6.1 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Step 3.5 Flash GGUF Q4 K S and how large is it?

Step 3.5 Flash GGUF Q4 K S is developed by stepfun-ai. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Step 3.5 Flash GGUF Q4 K S perform on standard benchmarks?

Step 3.5 Flash GGUF Q4 K S has the following published scores: LMSYS ELO 1394. Compare against reference models on this page or on the LLM Explorer leaderboards.

Step 3.5 Flash GGUF Q4 K S by stepfun-ai — VRAM 6.1GB, 256K context

Name: Step 3.5 Flash GGUF Q4 K S
Author: stepfun-ai

Step 3.5 Flash GGUF Q4 K S is an open-source language model by stepfun-ai. Features: LLM, VRAM: 6.1GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.41, ELO: 1394.

Arxiv:2507.19427 Arxiv:2601.05593 Arxiv:2602.10604 Conversational Custom code Endpoints compatible Gguf Imatrix Q4 Quantized Region:us Step3p5

Model Card on HF 🤗: https://huggingface.co/stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S

Step 3.5 Flash GGUF Q4 K S Benchmarks

LMSys ELO 1394 vs 1272 (so35) 9.6%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Step 3.5 Flash GGUF Q4 K S Parameters and Internals

LLM Name	Step 3.5 Flash GGUF Q4 K S
Repository 🤗	https://huggingface.co/stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S
Base Model(s)	stepfun-ai/step-3.5-flash stepfun-ai/step-3.5-flash
Required VRAM	6.1 GB
Updated	2026-08-08
Maintainer	stepfun-ai
Model Type	step3p5
Model Files	9.4 GB: 1-of-12 9.6 GB: 2-of-12 9.6 GB: 3-of-12 9.6 GB: 4-of-12 9.6 GB: 5-of-12 9.6 GB: 6-of-12 9.6 GB: 7-of-12 9.6 GB: 8-of-12 9.6 GB: 9-of-12 9.6 GB: 10-of-12 9.6 GB: 11-of-12 6.1 GB: 12-of-12
GGUF Quantization	Yes
Quantization Type	gguf\|q4\|q4_k
Model Architecture	Step3p5ForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Vocabulary Size	128896
Torch Data Type	bfloat16

Rank the Step 3.5 Flash GGUF Q4 K S capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation