Qwen3.8-2.4T-A95B
> [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with vLLM, SGLang, TokenSpeed, etc.
Params
2,446.2 B
Context
262,144
Downloads 30d
25 K
Likes
1,327
Download history
tracking started — chart appears after 7 days of snapshots (5 recorded)25 K downloads in the last 30 days
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 | 4,892.4 GB | 5,749.0 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 256K ctx | 4,892.4 GB | 17,123.8 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 -s https://aimodelscomparison.com/api/v1/models/qwen3-8-2-4t-a95b
{
"hf_id": "Qwen/Qwen3.8-2.4T-A95B",
"params_b": 2446.18,
"context_length": 262144,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 24938,
"vram_estimates": [
{ "quant": "bf16", "gb": 5749.0 }
],
"updated_at": "2026-10-19T06:02:31Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$2.00
input / 1M
$6.00
output / 1M
$0.25
cached input / 1M
$8.00
1M in + 1M out
- Context window
- 1,010,000 tokens
- Max output
- 909,000 tokens
- Providers
- 5
- Cheapest provider
- Alibaba · $2.00 / $6.00
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- 39.9 / 71.9 / 50.1
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- Qwen3_5MoeForCausalLM
- Parameters
- 2,446.2 B
- Tensor type
- BF16
- Context length
- 262,144
- Vocabulary
- 248,320
- Layers / heads
- 92 / 64
- Licence
- other
- First seen on the Hub
- 2026-08-08
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any text-generation model
Popular comparisons