IlyaGusev / text-generation updated 2 years ago

saiga_llama3_8b

Name: saiga_llama3_8b
Author: IlyaGusev

I've changed the prompt format from ChatML to the original Llama-3 format in v4. Don't forget to switch formats!

Params

8.0 B

Context

8,192

Downloads 30d

423 K

Likes

143

Licence: other Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

423 K412 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	bf16	16.1 GB	19.4 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 · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/saiga-llama3-8b
{
  "hf_id": "IlyaGusev/saiga_llama3_8b",
  "params_b": 8.03,
  "context_length": 8192,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 423303,
  "vram_estimates": [
    { "quant": "bf16", "gb": 19.4 }
  ],
  "updated_at": "2026-07-28T18:05:46Z"
}

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

Specifications

Architecture: LlamaForCausalLM
Parameters: 8.0 B
Tensor type: BF16
Context length: 8,192
Vocabulary: 128,256
Layers / heads: 32 / 32
Licence: other
First seen on the Hub: 2024-04-18
Training datasets: IlyaGusev/saiga_scored
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