Ornith-1.5-122B-GGUF
Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.
Params
122.0 B
Context
—
Downloads 30d
593 K
Likes
98
Download history
daily snapshots · 12 days593 K161 K
Oct 30Nov 3Nov 7Nov 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 |
|---|---|---|---|---|
| Ornith-1.5-122B-UD-IQ1_M.gguf | IQ1_M | 40.4 GB | 63.2 GB | ❌ Won’t fit |
| Ornith-1.5-122B-UD-IQ2_XXS.gguf | IQ2_XXS | 42.0 GB | 65.0 GB | ❌ Won’t fit |
| Ornith-1.5-122B-UD-Q2_K_XL.gguf | Q2_K_XL | 44.5 GB | 67.8 GB | ❌ Won’t fit |
| Ornith-1.5-122B-BF16-00006-of-00007.gguf | GGUF | 48.6 GB | 72.3 GB | ❌ Won’t fit |
| Ornith-1.5-122B-UD-IQ3_XXS.gguf | IQ3_XXS | 49.5 GB | 73.3 GB | ❌ Won’t fit |
| Ornith-1.5-122B-UD-Q3_K_XL-00002-of-00003.gguf | Q3_K_XL | 49.8 GB | 73.6 GB | ❌ Won’t fit |
| Ornith-1.5-122B-Q8_0-00003-of-00004.gguf | Q8 | 49.9 GB | 73.7 GB | ❌ Won’t fit |
| Ornith-1.5-122B-UD-Q4_K_XL-00002-of-00003.gguf | Q4_K_XL | 50.0 GB | 73.8 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 ornith-1-5-122b-gguf-unsloth # pin the quantization explicitly $ ollama run ornith-1-5-122b-gguf-unsloth-q4_k_xl
$ huggingface-cli download unsloth/Ornith-1.5-122B-GGUF-GGUF \
Ornith-1.5-122B-UD-Q4_K_XL-00002-of-00003.gguf --local-dir .
$ llama-cli -m Ornith-1.5-122B-UD-Q4_K_XL-00002-of-00003.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/ornith-1-5-122b-gguf-unsloth
{
"hf_id": "unsloth/Ornith-1.5-122B-GGUF",
"params_b": 122.00,
"context_length": null,
"license": { "id": "mit", "commercial": "yes" },
"downloads_30d": 593201,
"vram_estimates": [
{ "quant": "GGUF", "gb": 72.3 },
{ "quant": "IQ1_M", "gb": 63.2 }
],
"updated_at": "2026-10-30T01:00:36Z"
}
Specifications
- Parameters
- 122.0 B
- Licence
- mit
- First seen on the Hub
- 2026-10-20
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-30
Compare with any text-generation model