typhoon-ai / text-generation updated 1 month ago

typhoon2.5-qwen3-4b

Name: typhoon2.5-qwen3-4b
Author: typhoon-ai

Typhoon2.5-Qwen3-4B is a instruct Thai 🇹🇭 large language model with 4 billion parameters, a 256k context length, and function-calling capabilities. It is based on Qwen3 4B.

Params

4.0 B

Context

262,144

Downloads 30d

468 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

490 K463 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	8.0 GB	10.0 GB	✅ Runs comfortably
model.safetensors (bf16, full)	bf16 + 256K ctx	8.0 GB	28.6 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 · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/typhoon2-5-qwen3-4b
{
  "hf_id": "typhoon-ai/typhoon2.5-qwen3-4b",
  "params_b": 4.02,
  "context_length": 262144,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 468025,
  "vram_estimates": [
    { "quant": "bf16", "gb": 10.0 }
  ],
  "updated_at": "2026-07-28T18:05:22Z"
}

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

Specifications

Architecture: Qwen3ForCausalLM
Parameters: 4.0 B
Tensor type: BF16
Context length: 262,144
Vocabulary: 151,936
Layers / heads: 36 / 32
Licence: apache-2.0
First seen on the Hub: 2025-09-23
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3-8B 16.3 M Qwen2.5-1.5B-Instruct 14.0 M Qwen2.5-7B-Instruct 12.1 M Llama-3.1-8B-Instruct 8.0 M Qwen2.5-3B-Instruct 6.0 M Qwen3-4B 4.6 M

Appears in

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