EXAONE-3.5-7.8B-Instruct-AWQ
We introduce EXAONE 3.5, a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research. EXAONE 3.5 language models include: 1) 2.4B model optimized for deployment on small or resource-constrained devices, 2) 7.8B model matching the size of its predecessor but offering improved performance, and 3) 32B model delivering po...
Params
7.8 B
Context
32,768
Downloads 30d
578 K
Likes
18
Download history
daily snapshots · 55 days
▲ 2 K in the last 30 days (0.3%)
578 K211 K
Aug 22Sep 1Sep 11Sep 20
668 K211 K
Jul 28Aug 15Sep 2Sep 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 |
|---|---|---|---|---|
| model.safetensors | i32 | 5.3 GB | 7.5 GB | ✅ Runs comfortably |
| model.safetensors (bf16, full) | bf16 + 32K ctx | 5.3 GB | 11.0 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$ curl -s https://aimodelscomparison.com/api/v1/models/exaone-3-5-7-8b-instruct-awq
{
"hf_id": "LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct-AWQ",
"params_b": 7.82,
"context_length": 32768,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 577577,
"vram_estimates": [
{ "quant": "i32", "gb": 7.5 }
],
"updated_at": "2026-07-28T18:06:44Z"
}
Specifications
- Architecture
- ExaoneForCausalLM
- Parameters
- 7.8 B
- Tensor type
- I32
- Context length
- 32,768
- Vocabulary
- 102,400
- Licence
- other
- First seen on the Hub
- 2024-12-01
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any text-generation model
Popular comparisons
Appears in