unsloth
Qwen3.8 Flash Next
Qwen3.8 Flash Next is a 176.9B mixture-of-experts qwen4exp model from unsloth, with about 30.0B parameters active per token. Configured context length is 262,144 tokens. License: other. Quant sizes are the GGUF file bytes published on Hugging Face when a file exists.
Parameters177B / 30.0B active
Context256K
Attentionhybrid
Licenseother
48 layers · 2 KV heads · head dim 256 · 36 linear-attention layers · GGUF repo · config
Quant file sizes
| Quant | File size | Source |
|---|---|---|
| BF16 | 329.7 GB | Hugging Face file bytes |
| Q8_0 | 175.3 GB | Hugging Face file bytes |
| UD-Q6_K_XL | 157.5 GB | Hugging Face file bytes |
| UD-Q5_K_XL | 147.4 GB | Hugging Face file bytes |
| UD-Q4_K_XL | 103.7 GB | Hugging Face file bytes |
| UD-IQ4_XS | 87.2 GB | Hugging Face file bytes |
| UD-Q3_K_XL | 83.8 GB | Hugging Face file bytes |
| UD-IQ3_XXS | 76.3 GB | Hugging Face file bytes |
| UD-Q2_K_XL | 73.5 GB | Hugging Face file bytes |
| UD-IQ1_M | 69.4 GB | Hugging Face file bytes |
| UD-IQ1_S | 67.6 GB | Hugging Face file bytes |
On common machines
| Device | Verdict | Quant | Speed |
|---|---|---|---|
| GeForce RTX 4060 Ti 8GB | Won't fit | UD-IQ1_S | — |
| GeForce RTX 3060 12GB | Won't fit | UD-IQ1_S | — |
| GeForce RTX 4060 Ti 16GB | Won't fit | UD-IQ1_S | — |
| GeForce RTX 4090 | Won't fit | UD-IQ1_S | — |
| GeForce RTX 5090 | Won't fit | UD-IQ1_S | — |
| Apple M4 Pro | Won't fit | UD-IQ1_S | — |
| Apple M5 | Won't fit | UD-IQ1_S | — |
| CPU only · DDR5-5600 | Won't fit | UD-IQ1_S | — |
Smallest devices that fit it fully
- NVIDIA H100 SXM 80GB — Tight fit, UD-IQ1_M, 144–196 tok/s
- NVIDIA H100 PCIe 80GB — Tight fit, UD-IQ1_M, 86–117 tok/s
- NVIDIA A100 80GB SXM — Tight fit, UD-IQ1_M, 87–119 tok/s
- NVIDIA A100 80GB PCIe — Tight fit, UD-IQ1_M, 83–113 tok/s
- Apple M3 Ultra — Tight fit, UD-IQ1_S, 36–49 tok/s
- NVIDIA H200 SXM — Runs, UD-Q4_K_XL, 138–189 tok/s
Run it
Commands for the GeForce RTX 4060 Ti 16GB estimate (UD-IQ1_S).
llama.cpp
llama-server -hf unsloth/Qwen3.8-Flash-Next-GGUF:UD-IQ1_S -c 2048 -ngl 0
Ollama
ollama run qwen3.8-flash-next
LM Studio
lms get unsloth/Qwen3.8-Flash-Next-GGUF # Then load quant UD-IQ1_S