TinyLlama-1.1B-Chat-v0.3-GPTQ
Chat & support: TheBloke's Discord server Want to contribute? TheBloke's Patreon page TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)
Params
1.1 B
Context
2,048
Downloads 30d
195 K
Likes
10
Download history
daily snapshots · 56 days
▲ 383 K in the last 30 days (66.3%)
534 K195 K
Aug 23Sep 2Sep 12Sep 21
1.1 M195 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 | 0.8 GB | 1.5 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/tinyllama-1-1b-chat-v0-3-gptq
{
"hf_id": "TheBloke/TinyLlama-1.1B-Chat-v0.3-GPTQ",
"params_b": 1.10,
"context_length": 2048,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 194649,
"vram_estimates": [
{ "quant": "i32", "gb": 1.5 }
],
"updated_at": "2026-07-28T18:03:35Z"
}
Specifications
- Architecture
- LlamaForCausalLM
- Parameters
- 1.1 B
- Tensor type
- I32
- Context length
- 2,048
- Vocabulary
- 32,003
- Layers / heads
- 22 / 32
- Licence
- apache-2.0
- First seen on the Hub
- 2023-10-03
- Training datasets
- cerebras/SlimPajama-627B, bigcode/starcoderdata, OpenAssistant/oasst_top1_2023-08-25
- Added to our catalog
- 2026-07-28
Compare with any text-generation model