Model Intelligence Sheet
wesjos/Qwen3.5-4B-StreetTalk-GGUF overview
🧢 Qwen3.5 4B StreetTalk — GGUF Demos GGUF quant of wesjos/Qwen3.5 4B StreetTalk https://huggingface.co/wesjos/Qwen3.5 4B StreetTalk · repo: Qwen3.5 4B StreetT…
Runs locally from ~641.3 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | wesjos/Qwen3.5-4B-StreetTalk-GGUF |
|---|---|
| Author | wesjos |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | wesjos/Qwen3.5-4B-StreetTalk |
| Last modified | 2026-10-20T05:50:05.000Z |
Model README
---
license: apache-2.0
language:
- en
library_name: llama.cpp
pipeline_tag: text-generation
base_model: wesjos/Qwen3.5-4B-StreetTalk
tags:
- gguf
- qwen3.5
- conversational
- street-talk
- aave
- persona
- alignment
- dpo
- grpo
- concise
---
🧢 Qwen3.5-4B-StreetTalk — GGUF Demos
GGUF quant of wesjos/Qwen3.5-4B-StreetTalk · repo: Qwen3.5-4B-StreetTalk-GGUF
💬 Demo
📊 GRPO reward (JEV)
!JEV composite reward over 1,000 GRPO steps
🚀 Run it
llama-cli -m Qwen3.5-4B-StreetTalk.Q4_K_M.gguf -cnv -c 8192 --temp 0.7 --top-p 0.9Qwen3.5-4B-StreetTalk.Q4_K_M.gguf— 2.52 GiB (default)qwen3.5-4b-streettalk-q8_0.gguf— 4.29 GiB (near-lossless)Qwen3.5-4B-StreetTalk.F16-mmproj.gguf— 0.63 GiB (vision, optional)
License: Apache-2.0
Run wesjos/Qwen3.5-4B-StreetTalk-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models