bartowski / text-generation updated 1 year ago

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
Commercial use: conditional · llama3.2 Not gated GGUF 8 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days
165 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.

FileQuantSizeEst. VRAMVerdict 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 · Q4_0
$ ollama run llama-3-2-3b-instruct-gguf

# pin the quantization explicitly
$ ollama run llama-3-2-3b-instruct-gguf-q4_0
est. VRAM 2.6 GBon RTX 4090 · 24 GBJSON API →

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.