hugging-quants / text-generation updated 1 year ago

Meta-Llama-3.1-8B-Instruct-AWQ-INT4

Name: Meta-Llama-3.1-8B-Instruct-AWQ-INT4
Author: hugging-quants

> [!IMPORTANT] > This repository is a community-driven quantized version of the original model meta-llama/Meta-Llama-3.1-8B-Instruct which is the BF16 half-precision official version released by Meta AI.

Params

8.0 B

Context

131,072

Downloads 30d

167 K

Likes

Commercial use: conditional · llama3.1 Not gated SAFETENSORS 8 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

189 K167 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	5.7 GB	8.0 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 128K ctx	5.7 GB	26.1 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/meta-llama-3-1-8b-instruct-awq-int4
{
  "hf_id": "hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4",
  "params_b": 8.03,
  "context_length": 131072,
  "license": { "id": "llama3.1", "commercial": "conditional" },
  "downloads_30d": 167467,
  "vram_estimates": [
    { "quant": "i32", "gb": 8.0 }
  ],
  "updated_at": "2026-07-28T18:08:19Z"
}

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

Specifications

Architecture: LlamaForCausalLM
Parameters: 8.0 B
Tensor type: I32
Context length: 131,072
Vocabulary: 128,256
Layers / heads: 32 / 32
Licence: llama3.1
First seen on the Hub: 2024-07-19
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M Llama-3.1-8B-Instruct 8.0 M Qwen2.5-7B-Instruct-AWQ 4.6 M granite-4.1-8b 4.2 M

Appears in

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