Qwen3.8-Flash-Next-GGUF
Unsloth Dynamic v3.1 achieves superior accuracy & outperforms other leading quants. Nov 4 update: Dynamic v3.1 GGUF is here with 15% more accuracy, 50% less token use and 5% faster inference than other frontier quants. Scores the highest on Terminal Bench, DeepSWE & more! Details MTP is now available for 1.3-1.7x Faster inference in Unsloth. Read Guide To run, please use llama.cpp, Strata or use our Unsloth Desktop a...
Params
180.0 B
Context
—
Downloads 30d
1.7 M
Likes
1,554
Download history
daily snapshots · 63 days
▲ 392 K in the last 30 days (30.1%)
1.7 M1.0 M
Oct 12Oct 22Nov 1Nov 10
1.8 M936 K
Sep 9Sep 30Oct 21Nov 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 |
|---|---|---|---|---|
| mtp-Qwen3.8-Flash-Next-Q4_K_M.gguf | Q4_K_M | 2.8 GB | 30.6 GB | ❌ Won’t fit |
| mtp-Qwen3.8-Flash-Next-Q8_0.gguf | Q8_0 | 4.1 GB | 32.1 GB | ❌ Won’t fit |
| Qwen3.8-Flash-Next-UD-IQ1_S-00002-of-00003.gguf | IQ1_S | 37.6 GB | 68.8 GB | ❌ Won’t fit |
| Qwen3.8-Flash-Next-UD-IQ1_M-00002-of-00003.gguf | IQ1_M | 39.2 GB | 70.6 GB | ❌ Won’t fit |
| Qwen3.8-Flash-Next-UD-IQ2_XS-00002-of-00003.gguf | IQ2_XS | 47.0 GB | 79.2 GB | ❌ Won’t fit |
| Qwen3.8-Flash-Next-UD-IQ3_XXS-00002-of-00004.gguf | IQ3_XXS | 49.9 GB | 82.4 GB | ❌ Won’t fit |
| Qwen3.8-Flash-Next-Q8_0-00003-of-00006.gguf | Q8 | 54.4 GB | 87.3 GB | ❌ Won’t fit |
| Qwen3.8-Flash-Next-BF16-00003-of-00008.gguf | GGUF | 102.4 GB | 140.1 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
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
- 2026-09-09
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any image-text-to-text model