Qwopus3.6-27B-Fusion-GGUF
> Research preview. This model attempts to combine the reasoning capability of > Qwopus3.6-27B-v2 with the code-execution capability of Qwopus3.6-27B-Coder — in a single 27B > model, without significant loss to either skill. In practice it behaves like a production model > with both capabilities fused, but it has not yet been through a full rigorous evaluation. If you > find issues, please reach out on X — @kylehessl...
Params
—
Context
—
Downloads 30d
337 K
Likes
78
Download history
daily snapshots · 24 days338 K172 K
Aug 29Sep 6Sep 14Sep 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 |
|---|---|---|---|---|
| Qwopus3.6-27B-Fusion-Q3_K_M.gguf | Q3_K_M | 13.5 GB | 15.4 GB | ✅ Runs comfortably |
| Qwopus3.6-27B-Fusion-Q4_K_M.gguf | Q4_K_M | 16.8 GB | 19.0 GB | ✅ Runs comfortably |
| Qwopus3.6-27B-Fusion-Q5_K_M.gguf | Q5_K_M | 19.5 GB | 22.0 GB | ⚠️ Tight — reduce context |
| Qwopus3.6-27B-Fusion-Q6_K.gguf | Q6_K | 22.4 GB | 25.2 GB | ❌ Won’t fit |
| Qwopus3.6-27B-Fusion-Q8_0.gguf | Q8_0 | 29.0 GB | 32.5 GB | ❌ Won’t fit |
| Qwopus3.6-27B-Fusion-BF16.gguf | GGUF | 54.7 GB | 60.6 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 qwopus3-6-27b-fusion-gguf # pin the quantization explicitly $ ollama run qwopus3-6-27b-fusion-gguf-q4_k_m
$ huggingface-cli download KyleHessling1/Qwopus3.6-27B-Fusion-GGUF-GGUF \
Qwopus3.6-27B-Fusion-Q4_K_M.gguf --local-dir .
$ llama-cli -m Qwopus3.6-27B-Fusion-Q4_K_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/qwopus3-6-27b-fusion-gguf
{
"hf_id": "KyleHessling1/Qwopus3.6-27B-Fusion-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 336939,
"vram_estimates": [
{ "quant": "GGUF", "gb": 60.6 },
{ "quant": "Q3_K_M", "gb": 15.4 }
],
"updated_at": "2026-08-29T01:00:35Z"
}
Specifications
- Licence
- other
- First seen on the Hub
- 2026-07-20
- Base model
- Qwen3.6-27B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-29
Compare with any text-generation model