Llama-3.2-3B-Instruct-GGUF
Filename Quant type File Size Split Description -------- ---------- --------- ----- ----------- Llama-3.2-3B-Instruct-f16.gguf f16 6.43GB false Full F16 weights. Llama-3.2-3B-Instruct-Q80.gguf Q80 3.42GB false Extremely high quality, generally unneeded but max available quant. Llama-3.2-3B-Instruct-Q6KL.gguf Q6KL 2.74GB false Uses Q80 for embed and output weights. Very high quality, near perfect, recommended. Llama-3...
Params
—
Context
—
Downloads 30d
157 K
Likes
229
Download history
daily snapshots · 10 days165 K157 K
Jul 28Jul 31Aug 3Aug 6
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 |
|---|---|---|---|---|
| Llama-3.2-3B-Instruct-IQ3_M.gguf | IQ3_M | 1.6 GB | 2.3 GB | ✅ Runs comfortably |
| Llama-3.2-3B-Instruct-IQ4_XS.gguf | IQ4_XS | 1.8 GB | 2.5 GB | ✅ Runs comfortably |
| Llama-3.2-3B-Instruct-Q3_K_L.gguf | Q3_K_L | 1.8 GB | 2.5 GB | ✅ Runs comfortably |
| Llama-3.2-3B-Instruct-Q3_K_XL.gguf | Q3_K_XL | 1.9 GB | 2.6 GB | ✅ Runs comfortably |
| Llama-3.2-3B-Instruct-Q4_0.gguf | Q4_0 | 1.9 GB | 2.6 GB | ✅ Runs comfortably |
| Llama-3.2-3B-Instruct-Q4_0_4_4.gguf | Q4_0_4_4 | 1.9 GB | 2.6 GB | ✅ Runs comfortably |
| Llama-3.2-3B-Instruct-Q4_0_4_8.gguf | Q4_0_4_8 | 1.9 GB | 2.6 GB | ✅ Runs comfortably |
| Llama-3.2-3B-Instruct-Q4_0_8_8.gguf | Q4_0_8_8 | 1.9 GB | 2.6 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 llama-3-2-3b-instruct-gguf # pin the quantization explicitly $ ollama run llama-3-2-3b-instruct-gguf-q4_0
$ huggingface-cli download bartowski/Llama-3.2-3B-Instruct-GGUF-GGUF \
Llama-3.2-3B-Instruct-Q4_0.gguf --local-dir .
$ llama-cli -m Llama-3.2-3B-Instruct-Q4_0.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/llama-3-2-3b-instruct-gguf
{
"hf_id": "bartowski/Llama-3.2-3B-Instruct-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "llama3.2", "commercial": "conditional" },
"downloads_30d": 157374,
"vram_estimates": [
{ "quant": "IQ3_M", "gb": 2.3 },
{ "quant": "IQ4_XS", "gb": 2.5 }
],
"updated_at": "2026-07-28T18:08:54Z"
}
Specifications
- Licence
- llama3.2
- First seen on the Hub
- 2024-09-25
- Base model
- Llama-3.2-3B-Instruct
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Family
Base model and the most-downloaded derivatives in the catalog.
Sponsored · GPU cloud
Not enough VRAM?
Spin up a 24 GB L4 instance in 40 seconds. $0.44/hr.