Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata
Qwen's original Qwen3.8-Flash-Next with every routed expert in NVFP4, quantized from the BF16 checkpoint by GPTQ, packed for Strata NVFP4: the 125B hybrid MoE on one RTX 20-50 card (12 GB of VRAM or more) and 64 GB of RAM or more.
Params
180.0 B
Context
—
Downloads 30d
245 K
Likes
38
Download history
tracking started — chart appears after 7 days of snapshots (4 recorded)245 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 |
|---|---|---|---|---|
| ple-fp8.gguf | GGUF | 51.2 GB | 83.8 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$ ollama run qwen3-8-flash-next-nvfp4-gptq-strata # pin the quantization explicitly $ ollama run qwen3-8-flash-next-nvfp4-gptq-strata-gguf
$ huggingface-cli download Maximilian228/Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata-GGUF \
ple-fp8.gguf --local-dir .
$ llama-cli -m ple-fp8.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen3-8-flash-next-nvfp4-gptq-strata
{
"hf_id": "Maximilian228/Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata",
"params_b": 180.00,
"context_length": null,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 244900,
"vram_estimates": [
{ "quant": "GGUF", "gb": 83.8 }
],
"updated_at": "2026-10-22T01:00:20Z"
}
Specifications
- Parameters
- 180.0 B
- Licence
- other
- First seen on the Hub
- 2026-10-09
- Base model
- Qwen3.8-Flash-Next
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-22
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model