RedHatAI / text-generation updated 6 months ago

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

Download history

daily snapshots · 56 days
▲ 281 K in the last 30 days (58.3%)
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.

FileQuantSizeEst. VRAMVerdict 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 · api/v1
$ 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"
}
est. VRAM —on RTX 4090 · 24 GBJSON API →

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