Diplodocus-preview-GGUF
Diplodocus preview 4, the Osaurus assistant for finance, documents, spreadsheets and tool-assisted work, built on IFM/K2-Horizon-7B and trained on Osaurus' own workspace tools (workbooks and documents edited in place, the built-in calculate tool, reasoning on and off). This is the GGUF build for llama.cpp in three calibrated sizes:
Params
—
Context
—
Downloads 30d
663 K
Likes
1
Download history
daily snapshots · 12 days663 K154 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 |
|---|---|---|---|---|
| Diplodocus-preview.imatrix.gguf | GGUF | 0.0 GB | 0.5 GB | ✅ Runs comfortably |
| Diplodocus-preview-Q4_K_M.gguf | Q4_K_M | 6.3 GB | 7.5 GB | ✅ Runs comfortably |
| Diplodocus-preview-Q6_K.gguf | Q6_K | 7.8 GB | 9.0 GB | ✅ Runs comfortably |
| Diplodocus-preview-Q8_0.gguf | Q8_0 | 9.6 GB | 11.0 GB | ✅ Runs comfortably |
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 diplodocus-preview-gguf # pin the quantization explicitly $ ollama run diplodocus-preview-gguf-q4_k_m
$ huggingface-cli download OsaurusAI/Diplodocus-preview-GGUF-GGUF \
Diplodocus-preview-Q4_K_M.gguf --local-dir .
$ llama-cli -m Diplodocus-preview-Q4_K_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/diplodocus-preview-gguf
{
"hf_id": "OsaurusAI/Diplodocus-preview-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 663298,
"vram_estimates": [
{ "quant": "Q4_K_M", "gb": 7.5 },
{ "quant": "Q6_K", "gb": 9.0 }
],
"updated_at": "2026-10-30T01:00:41Z"
}
Specifications
- Licence
- apache-2.0
- First seen on the Hub
- 2026-10-15
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-30
Compare with any text-generation model
Appears in