Qwen3-Coder-Next-FP8-dynamic
- Model Architecture: Qwen3NextForCausalLM - Input: Text - Output: Text - Model Optimizations: - Weight quantization: FP8 - Activation quantization: FP8 - Release Date: - Version: 1.0 - Model Developers:: Red Hat
Params
79.8 B
Context
262,144
Downloads 30d
201 K
Likes
2
Download history
daily snapshots · 56 days
▲ 281 K in the last 30 days (58.3%)
442 K201 K
Aug 23Sep 2Sep 12Sep 21
864 K201 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 | f8_e4m3 | 81.7 GB | 102.4 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 256K ctx | 81.7 GB | 473.2 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-coder-next-fp8-dynamic
{
"hf_id": "RedHatAI/Qwen3-Coder-Next-FP8-dynamic",
"params_b": 79.75,
"context_length": 262144,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 200940,
"vram_estimates": [
{ "quant": "f8_e4m3", "gb": 102.4 }
],
"updated_at": "2026-07-28T18:04:48Z"
}
Specifications
- Architecture
- Qwen3NextForCausalLM
- Parameters
- 79.8 B
- Tensor type
- F8_E4M3
- Context length
- 262,144
- Vocabulary
- 151,936
- Layers / heads
- 48 / 16
- Licence
- apache-2.0
- First seen on the Hub
- 2026-02-27
- Base model
- Qwen3-Coder-Next
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model