POCKET-Darwin-180B-GGUF
A 180B frontier model from a laptop to DGX Spark. A 4-bit GGUF build of Darwin-180B-RSI-R3 (111.3 GB, 4 files) for llama.cpp. It runs on a gaming laptop with an 8 GB GPU and 32 GB RAM, a 128 GB mini PC, a CPU-only server, a single datacenter GPU, or NVIDIA DGX Spark.
Params
180.0 B
Context
—
Downloads 30d
239 K
Likes
64
Download history
tracking started — chart appears after 7 days of snapshots (6 recorded)239 K downloads in the last 30 days
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 |
|---|---|---|---|---|
| POCKET-Darwin-180B-UD-Q4_K_XL-00002-of-00004.gguf | Q4_K_XL | 49.9 GB | 82.3 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 pocket-darwin-180b-gguf # pin the quantization explicitly $ ollama run pocket-darwin-180b-gguf-q4_k_xl
$ huggingface-cli download FINAL-Bench/POCKET-Darwin-180B-GGUF-GGUF \
POCKET-Darwin-180B-UD-Q4_K_XL-00002-of-00004.gguf --local-dir .
$ llama-cli -m POCKET-Darwin-180B-UD-Q4_K_XL-00002-of-00004.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/pocket-darwin-180b-gguf
{
"hf_id": "FINAL-Bench/POCKET-Darwin-180B-GGUF",
"params_b": 180.00,
"context_length": null,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 238647,
"vram_estimates": [
{ "quant": "Q4_K_XL", "gb": 82.3 }
],
"updated_at": "2026-10-20T01:00:28Z"
}
Specifications
- Parameters
- 180.0 B
- Licence
- other
- First seen on the Hub
- 2026-10-02
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any text-generation model