Model Intelligence Sheet
RockMan256/Qwen3.5-2B-home16k-GGUF overview
Qwen3.5 2B home16k GGUF GGUF quantizations of RockMan256/Qwen3.5 2B home16k https://huggingface.co/RockMan256/Qwen3.5 2B home16k . Converted using llama.cpp ht…
Runs locally from ~637.3 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | RockMan256/Qwen3.5-2B-home16k-GGUF |
|---|---|
| Author | RockMan256 |
| Pipeline | — |
| License | — |
| Base model | RockMan256/Qwen3.5-2B-home16k |
| Last modified | 2026-07-11T09:52:41.000Z |
Model README
---
base_model: RockMan256/Qwen3.5-2B-home16k
library_name: llama-cpp
---
Qwen3.5-2B-home16k-GGUF
GGUF quantizations of RockMan256/Qwen3.5-2B-home16k.
Converted using llama.cpp.
Files
| File | Type | Size |
|------|------|------|
| qwen3.5-2B-home16k-Q4_K_M.gguf | Text model (Q4_K_M) | 1.3 GB |
| mmproj-model-f16.gguf | Vision projector (F16) | 638 MB |
Usage
llama.cpp CLI
./llama-server \
-m qwen3.5-2B-home16k-Q4_K_M.gguf \
--mmproj mmproj-model-f16.gguf \
--host 0.0.0.0 --port 8080Open WebUI
- Go to Settings > Connections > Model Ollama
- Set the API URL to your llama.cpp server endpoint
- Upload both
qwen3.5-2B-home16k-Q4_K_M.ggufandmmproj-model-f16.gguf
Source Model
- Base: Qwen3.5-2B
- Fine-tuned: RockMan256/Qwen3.5-2B-home16k (16k context, vision support)
Run RockMan256/Qwen3.5-2B-home16k-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models