taardis-27b-full-ternary
A 27-billion-parameter transformer at 1.75 bits per weight — 5.90 GB — where every weight is a ternary integer {-1, 0, +1} × scale: body, attention, MLP, LM head and embedding table included, with norms and group scales on the integer grid too (balanced-ternary digit stacks). And V2 ships the pipeline's correction system: The Doctors — 496 cross-layer low-rank ternary branches that ride alongside the frozen weights a...
Params
—
Context
—
Downloads 30d
268 K
Likes
10
Download history
daily snapshots · 14 days268 K249 K
Sep 8Sep 12Sep 17Sep 21
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 |
|---|---|---|---|---|
| TAARDIS-27B-Full-Ternary-V1.gguf | GGUF | 7.2 GB | 8.4 GB | ✅ Runs comfortably |
| model.safetensors | fp16 | 24.4 GB | 27.4 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 taardis-27b-full-ternary # pin the quantization explicitly $ ollama run taardis-27b-full-ternary-gguf
$ huggingface-cli download CodeMasterCody3D/taardis-27b-full-ternary-GGUF \
TAARDIS-27B-Full-Ternary-V1.gguf --local-dir .
$ llama-cli -m TAARDIS-27B-Full-Ternary-V1.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/taardis-27b-full-ternary
{
"hf_id": "CodeMasterCody3D/taardis-27b-full-ternary",
"params_b": null,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 267886,
"vram_estimates": [
{ "quant": "GGUF", "gb": 8.4 },
{ "quant": "fp16", "gb": 27.4 }
],
"updated_at": "2026-09-17T01:00:23Z"
}
Specifications
- Licence
- apache-2.0
- First seen on the Hub
- 2026-09-03
- Base model
- Qwen3.8-27B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-08
Compare with any text-generation model