Qwen2.5-14B-Instruct-GGUF
Filename Quant type File Size Split Description -------- ---------- --------- ----- ----------- Qwen2.5-14B-Instruct-f16.gguf f16 29.55GB false Full F16 weights. Qwen2.5-14B-Instruct-Q80.gguf Q80 15.70GB false Extremely high quality, generally unneeded but max available quant. Qwen2.5-14B-Instruct-Q6KL.gguf Q6KL 12.50GB false Uses Q80 for embed and output weights. Very high quality, near perfect, recommended. Qwen2.5...
Params
14.0 B
Context
32,768
Downloads 30d
154 K
Likes
74
Download history
tracking started — chart appears after 7 days of snapshots (3 recorded)154 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 |
|---|---|---|---|---|
| Qwen2.5-14B-Instruct-IQ2_M.gguf | IQ2_M | 5.4 GB | 8.5 GB | ✅ Runs comfortably |
| Qwen2.5-14B-Instruct-Q2_K.gguf | Q2_K | 5.8 GB | 8.9 GB | ✅ Runs comfortably |
| Qwen2.5-14B-Instruct-IQ3_XS.gguf | IQ3_XS | 6.4 GB | 9.6 GB | ✅ Runs comfortably |
| Qwen2.5-14B-Instruct-Q2_K_L.gguf | Q2_K_L | 6.5 GB | 9.8 GB | ✅ Runs comfortably |
| Qwen2.5-14B-Instruct-IQ3_M.gguf | IQ3_M | 6.9 GB | 10.2 GB | ✅ Runs comfortably |
| Qwen2.5-14B-Instruct-Q3_K_M.gguf | Q3_K_M | 7.3 GB | 10.7 GB | ✅ Runs comfortably |
| Qwen2.5-14B-Instruct-Q3_K_L.gguf | Q3_K_L | 7.9 GB | 11.3 GB | ✅ Runs comfortably |
| Qwen2.5-14B-Instruct-IQ4_XS.gguf | IQ4_XS | 8.1 GB | 11.5 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 qwen2-5-14b-instruct-gguf # pin the quantization explicitly $ ollama run qwen2-5-14b-instruct-gguf-iq2_m
$ huggingface-cli download bartowski/Qwen2.5-14B-Instruct-GGUF-GGUF \
Qwen2.5-14B-Instruct-IQ2_M.gguf --local-dir .
$ llama-cli -m Qwen2.5-14B-Instruct-IQ2_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen2-5-14b-instruct-gguf
{
"hf_id": "bartowski/Qwen2.5-14B-Instruct-GGUF",
"params_b": 14.00,
"context_length": 32768,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 154274,
"vram_estimates": [
{ "quant": "IQ2_M", "gb": 8.5 },
{ "quant": "IQ3_M", "gb": 10.2 }
],
"updated_at": "2026-10-23T01:00:17Z"
}
Specifications
- Parameters
- 14.0 B
- Context length
- 32,768
- Licence
- apache-2.0
- First seen on the Hub
- 2024-09-17
- Base model
- Qwen2.5-14B-Instruct
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-23
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model