Qwen3.6-27B-GGUF
> 🆕 Newer model available — Qwen3.8-27B GGUF > Qwen's 2026-08 release. Same 27B class, six quants from 10 GB, vision included, Korean-verified. > ollama run batiai/qwen3.8-27b:iq4
Params
27.0 B
Context
—
Downloads 30d
150 K
Likes
8
Download history
daily snapshots · 90 days
▲ 7 K in the last 30 days (4.6%)
157 K147 K
Sep 26Oct 6Oct 16Oct 25
159 K147 K
Jul 28Aug 27Sep 26Oct 25
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 |
|---|---|---|---|---|
| mmproj-Qwen-Qwen3.6-27B-BF16.gguf | GGUF | 0.9 GB | 5.6 GB | ✅ Runs comfortably |
| Qwen-Qwen3.6-27B-IQ3_XXS.gguf | IQ3_XXS | 11.2 GB | 16.9 GB | ✅ Runs comfortably |
| Qwen-Qwen3.6-27B-Q3_K_M.gguf | Q3_K_M | 13.3 GB | 19.2 GB | ✅ Runs comfortably |
| Qwen-Qwen3.6-27B-IQ4_XS.gguf | IQ4_XS | 15.1 GB | 21.1 GB | ⚠️ Tight — reduce context |
| Qwen-Qwen3.6-27B-Q4_K_M.gguf | Q4_K_M | 16.5 GB | 22.8 GB | ⚠️ Tight — reduce context |
| Qwen-Qwen3.6-27B-Q6_K.gguf | Q6_K | 22.1 GB | 28.8 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 qwen3-6-27b-gguf # pin the quantization explicitly $ ollama run qwen3-6-27b-gguf-q4_k_m
$ huggingface-cli download batiai/Qwen3.6-27B-GGUF-GGUF \
Qwen-Qwen3.6-27B-Q4_K_M.gguf --local-dir .
$ llama-cli -m Qwen-Qwen3.6-27B-Q4_K_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen3-6-27b-gguf
{
"hf_id": "batiai/Qwen3.6-27B-GGUF",
"params_b": 27.00,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 149546,
"vram_estimates": [
{ "quant": "IQ3_XXS", "gb": 16.9 },
{ "quant": "IQ4_XS", "gb": 21.1 }
],
"updated_at": "2026-10-19T01:00:19Z"
}
Specifications
- Parameters
- 27.0 B
- Licence
- apache-2.0
- First seen on the Hub
- 2026-04-23
- Base model
- Qwen3.6-27B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any text-generation model