richardyoung/
sensenova-si-2b:iq4_xs

1 5 days ago

sensenova-si-2b is a ~2B-parameter Qwen2-architecture model from sensenova/sensenova-si (built on OpenGVLab’s InternVL3‑2B) converted to GGUF for llama.cpp/Ollama, with 32K context and two published quants: Q4_K_M (recommended) and iq4_xs (smaller).

5 days ago

bff757c37444 · 1.0GB ·

model
qwen2
·
1.78B
·
IQ4_XS
template
{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user
params
{ "stop": [ "<|im_start|>", "<|im_end|>" ] }

Readme

SenseNova-SI-2B: GGUF quantizations for Ollama

Overview

SenseNova-SI-2B is a GGUF conversion of sensenova/sensenova-si for llama.cpp / Ollama. Upstream: https://huggingface.co/sensenova/sensenova-si

Notes

Alias matches existing local artifacts; adjust if needed.

Key Details

Status

  • Local GGUFs: present

Available Versions

Tag GGUF Size RAM (est.) Notes
IQ4_XS SenseNova-SI-2B-IQ4_XS.gguf 0.96 GiB 2 GiB
Q4_K_M SenseNova-SI-2B-Q4_K_M.gguf 1.04 GiB 3 GiB Recommended

Quick Start

ollama run richardyoung/sensenova-si-2b:q4_k_m "Hello!"

Available Commands

  • ollama run richardyoung/sensenova-si-2b:iq4_xs
  • ollama run richardyoung/sensenova-si-2b:q4_k_m

License

See the upstream repo for license/terms: https://huggingface.co/sensenova/sensenova-si

Acknowledgments

  • Quantized with llama.cpp (llama-quantize).
  • GGUF conversion via llama.cpp (convert_hf_to_gguf.py).