Llama-3.2-1B-Instruct-GGUF
MaziyarPanahi/Llama-3.2-1B-Instruct-GGUF contains GGUF format model files for meta-llama/Llama-3.2-1B-Instruct.
Params
—
Context
—
Downloads 30d
183 K
Likes
18
Download history
daily snapshots · 32 days
▲ 0 in the last 30 days (0.0%)
183 K183 K
Aug 22Sep 1Sep 11Sep 20
183 K183 K
Aug 20Aug 30Sep 10Sep 20
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-3.2-1B-Instruct.IQ1_S.gguf | IQ1_S | 0.4 GB | 0.9 GB | ✅ Runs comfortably |
| Llama-3.2-1B-Instruct.IQ1_M.gguf | IQ1_M | 0.4 GB | 1.0 GB | ✅ Runs comfortably |
| Llama-3.2-1B-Instruct.IQ2_XS.gguf | IQ2_XS | 0.5 GB | 1.0 GB | ✅ Runs comfortably |
| Llama-3.2-1B-Instruct.Q2_K.gguf | Q2_K | 0.6 GB | 1.1 GB | ✅ Runs comfortably |
| Llama-3.2-1B-Instruct.IQ3_XS.gguf | IQ3_XS | 0.6 GB | 1.2 GB | ✅ Runs comfortably |
| Llama-3.2-1B-Instruct.IQ4_XS.gguf | IQ4_XS | 0.7 GB | 1.3 GB | ✅ Runs comfortably |
| Llama-3.2-1B-Instruct.Q3_K_L.gguf | Q3_K_L | 0.7 GB | 1.3 GB | ✅ Runs comfortably |
| Llama-3.2-1B-Instruct.Q3_K_M.gguf | Q3_K_M | 0.7 GB | 1.3 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-3-2-1b-instruct-gguf-maziyarpanahi # pin the quantization explicitly $ ollama run llama-3-2-1b-instruct-gguf-maziyarpanahi-iq1_m
$ huggingface-cli download MaziyarPanahi/Llama-3.2-1B-Instruct-GGUF-GGUF \
Llama-3.2-1B-Instruct.IQ1_M.gguf --local-dir .
$ llama-cli -m Llama-3.2-1B-Instruct.IQ1_M.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/llama-3-2-1b-instruct-gguf-maziyarpanahi
{
"hf_id": "MaziyarPanahi/Llama-3.2-1B-Instruct-GGUF",
"params_b": null,
"context_length": null,
"license": { "id": "", "commercial": "unknown" },
"downloads_30d": 182757,
"vram_estimates": [
{ "quant": "IQ1_M", "gb": 1.0 },
{ "quant": "IQ1_S", "gb": 0.9 }
],
"updated_at": "2026-08-20T01:00:43Z"
}
Specifications
- First seen on the Hub
- 2024-09-25
- Base model
- Llama-3.2-1B-Instruct
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-20
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model