casperhansen / text-generation updated 1 year ago

llama-3.3-70b-instruct-awq

Name: llama-3.3-70b-instruct-awq
Author: casperhansen

This is the AWQ version of the Llama 3.3 70B Instruct model. Find more info here: https://github.com/casper-hansen/AutoAWQ.

Params

70.6 B

Context

131,072

Downloads 30d

426 K

Likes

Commercial use: conditional · llama3.3 Not gated SAFETENSORS 8 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

426 K266 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
model.safetensors	i32	39.8 GB	54.8 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 128K ctx	39.8 GB	213.6 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

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/llama-3-3-70b-instruct-awq
{
  "hf_id": "casperhansen/llama-3.3-70b-instruct-awq",
  "params_b": 70.55,
  "context_length": 131072,
  "license": { "id": "llama3.3", "commercial": "conditional" },
  "downloads_30d": 425751,
  "vram_estimates": [
    { "quant": "i32", "gb": 54.8 }
  ],
  "updated_at": "2026-07-28T18:07:06Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: LlamaForCausalLM
Parameters: 70.6 B
Tensor type: I32
Context length: 131,072
Vocabulary: 128,256
Layers / heads: 80 / 64
Licence: llama3.3
First seen on the Hub: 2024-12-06
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3.6-35B-A3B-NVFP4 11.3 M gpt-oss-20b 8.6 M Qwen3-32B 8.3 M dolphin-2.9.1-yi-1.5-34b 4.6 M gpt-oss-120b 4.2 M NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 2.8 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB