Qwen3.8-Flash-Next-GGUF
Built from Qwen's original weights with our own importance matrix. The calibration corpora behind our builds are public. Built by the team behind Atomic Chat, the app that runs open-weight models locally and offline. Qwen3.8-Flash-Next is the first open-weight release of the architecture behind Qwen4. These GGUFs are self-quantized from Qwen's original weights with our own importance matrix, published alongside the q...
Params
180.0 B
Context
—
Downloads 30d
467 K
Likes
206
Download history
daily snapshots · 53 days
▲ 294 K in the last 30 days (38.7%)
776 K467 K
Oct 12Oct 22Nov 1Nov 10
776 K226 K
Sep 19Oct 6Oct 24Nov 10
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 |
|---|---|---|---|---|
| mmproj-Qwen3.8-Flash-Next-BF16.gguf | GGUF | 0.9 GB | 28.5 GB | ❌ Won’t fit |
| Qwen3.8-Flash-Next-AD-3.84bpw-IQ4_XS-M64-00001-of-00003.gguf | IQ4_XS | 44.9 GB | 76.9 GB | ❌ Won’t fit |
| Qwen3.8-Flash-Next-AD-4.27bpw-Q4_K_M-M64-00001-of-00003.gguf | Q4_K_M | 44.9 GB | 76.9 GB | ❌ Won’t fit |
| Qwen3.8-Flash-Next-AD-5.00bpw-Q5_K_M-M64-00003-of-00003.gguf | Q5_K_M | 54.4 GB | 87.3 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-gguf-atomicchat # pin the quantization explicitly $ ollama run qwen3-8-flash-next-gguf-atomicchat-q4_k_m
$ huggingface-cli download AtomicChat/Qwen3.8-Flash-Next-GGUF-GGUF \
Qwen3.8-Flash-Next-AD-4.27bpw-Q4_K_M-M64-00001-of-00003.gguf --local-dir .
$ llama-cli -m Qwen3.8-Flash-Next-AD-4.27bpw-Q4_K_M-M64-00001-of-00003.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/qwen3-8-flash-next-gguf-atomicchat
{
"hf_id": "AtomicChat/Qwen3.8-Flash-Next-GGUF",
"params_b": 180.00,
"context_length": null,
"license": { "id": "other", "commercial": "unknown" },
"downloads_30d": 467020,
"vram_estimates": [
{ "quant": "IQ4_XS", "gb": 76.9 },
{ "quant": "Q4_K_M", "gb": 76.9 }
],
"updated_at": "2026-10-30T01:00:22Z"
}
Specifications
- Parameters
- 180.0 B
- Licence
- other
- First seen on the Hub
- 2026-08-26
- Base model
- Qwen3.8-Flash-Next
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-19
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model