Downloads · 30 days
41
10% of all-time downloads
Step-3.5-Flash-GGUF-Q4_K_M
ramgpt/Step-3.5-Flash-GGUF-Q4_K_M
Step-3.5-Flash-GGUF-Q4_K_M is a machine learning model from ramgpt. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
This repository provides a q4km-quantized GGUF file derived from stepfun-ai/Step-3.5-Flash.
All-time downloads
409
Public
Repo size
119 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf119 GB · 100%
At a glance
- License
- other
- Access
- Public
- Created
- Feb 7, 2026
- Updated
- Feb 7, 2026
- SHA
- 3bae2d6d
Base models
Model card
From the Hugging Face model README
stepfun-ai-Step-3.5-Flash.F16.Q4_K_M.gguf
Overview (EN)
This repository provides a q4_k_m-quantized GGUF file derived from stepfun-ai/Step-3.5-Flash.
Quick Start (llama.cpp)
./build/bin/llama-cli -m stepfun-ai-Step-3.5-Flash.F16.Q4_K_M.gguf -p "Hello"
Quantization
- Format: GGUF
- Method: q4_k_m
- File:
stepfun-ai-Step-3.5-Flash.F16.Q4_K_M.gguf - Size: ~110.44 GB
Provenance
- Base model:
stepfun-ai/Step-3.5-Flash
Note: This repo contains inference-only quantized weights. Respect the upstream license and usage terms.
Présentation (FR)
Ce dépôt fournit un fichier GGUF q4_k_m issu de stepfun-ai/Step-3.5-Flash.
Démarrage rapide (llama.cpp)
./build/bin/llama-cli -m stepfun-ai-Step-3.5-Flash.F16.Q4_K_M.gguf -p "Bonjour"
Quantification
- Format : GGUF
- Méthode : q4_k_m
- Fichier :
stepfun-ai-Step-3.5-Flash.F16.Q4_K_M.gguf - Taille : ~110.44 Go
Provenance
- Modèle amont :
stepfun-ai/Step-3.5-Flash
Remarque : Ce dépôt contient uniquement des poids quantifiés pour l'inférence. Merci de respecter la licence et les conditions d'utilisation du modèle d'origine.
- License
- other
- Languages
- en, fr
- Created
- Feb 7, 2026
- Updated
- Feb 7, 2026