llama-3.3-70b-instruct-awq
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
507 K
Likes
46
Download history
daily snapshots · 56 days
▲ 233 K in the last 30 days (31.5%)
822 K460 K
Aug 23Sep 2Sep 12Sep 21
822 K266 K
Jul 28Aug 15Sep 3Sep 21
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 -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": 507212,
"vram_estimates": [
{ "quant": "i32", "gb": 54.8 }
],
"updated_at": "2026-07-28T18:07:06Z"
}
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 any text-generation model