Sage-A1.5-Q8_0-GGUF
> [!Note] > This repository contains GGUF model weights for Sage-A1.5, quantized to Q80, for deployment with llama.cpp, Ollama, LM Studio, and other GGUF-compatible runtimes. > > For the original Hugging Face Transformers weights (compatible with Transformers, vLLM, SGLang, etc.), see InternScience/Sage-A1.5.
Params
—
Context
—
Downloads 30d
490 K
Likes
17
Download history
daily snapshots · 13 days490 K140 K
Oct 29Nov 2Nov 6Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| Sage-A1.5-mmproj.gguf | GGUF | 0.9 GB | 1.5 GB | ✅ Runs comfortably |
| Sage-A1.5-Q8_0.gguf | Q8_0 | 37.8 GB | 42.1 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ ollama run sage-a1-5-q8-0-gguf # pin the quantization explicitly $ ollama run sage-a1-5-q8-0-gguf-q8_0
$ huggingface-cli download InternScience/Sage-A1.5-Q8_0-GGUF-GGUF \
Sage-A1.5-Q8_0.gguf --local-dir .
$ llama-cli -m Sage-A1.5-Q8_0.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/sage-a1-5-q8-0-gguf
{
"hf_id": "InternScience/Sage-A1.5-Q8_0-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 489596,
"vram_estimates": [
{ "quant": "Q8_0", "gb": 42.1 },
{ "quant": "GGUF", "gb": 1.5 }
],
"updated_at": "2026-10-29T01:00:35Z"
}
Specifications
- Licence
- apache-2.0
- First seen on the Hub
- 2026-10-21
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-29
Compare with any text-generation model
Appears in