👋 Join our WeChat or Discord community. 📖 Check out the GLM-5.3-Flash blog and GLM-5 Technical report . 📍 Use GLM-5.3-Flash API services on Z.ai API Platform.
Qwen3.8-Flash-Next
Qwen·Instruct·released 24 Aug 2026
ollama run qwen3.8-flash-nextQwen3.8-Flash-Next is an instruct-tuned vision-language model from Qwen. It uses a mixture-of-experts design with 180B total parameters and 61.6B active parameters. It accepts text and image inputs and returns text, with a context length of 262,144 tokens. It is released under the qwen-community-1.0 licence, which allows limited commercial use. No other sizes in a model family are listed for it.
How much VRAM does Qwen3.8-Flash-Next need?
At Q4_K_M Qwen3.8-Flash-Next needs about 108 GB with an 8K context (108 GB at Q4, 353 GB at full precision). Pick your GPU to see what fits and how fast it runs.
Needs: ≈108 GB · Q4_K_M · 8K context — Pick a GPU to check the fit.
Advanced: context 8K · KV cache 16-bit
Smallest GPU for each quant and context (KV cache 16-bit)
| Quantisation | 8K | 16K | 32K | 64K | 128K | 256K |
|---|---|---|---|---|---|---|
| Q3_K_M | ||||||
| Q4_K_M | ||||||
| Q5_K_M | ||||||
| Q6_K | ||||||
| Q8_0 | ||||||
| FP16 |
≤16 GB card24–32 GB48–96 GBmore
| Quantisation | Total |
|---|---|
| Q2_KHeavy lossSmallest, noticeably worse quality | ≈59 GB |
| Q3_K_MNoticeable lossSmall, some quality loss | ≈87 GB |
| Q4_K_MrecommendedSmall lossRecommended default for local use | ≈108 GB |
| Q5_K_MNear-losslessNear-lossless for most tasks | ≈126 GB |
| Q6_KNear-losslessPractically lossless | ≈146 GB |
| Q8_0LosslessLossless in practice, twice the size of Q4 | ≈185 GB |
| FP16 / BF16LosslessFull precision, as released | ≈347 GB |
Estimates for 8K tokens of context: weights + KV cache + runtime overhead. All experts stay in memory, but only the active ones are read per token. Speed assumes memory-bound decoding at your GPU’s bandwidth. Pick a GPU above and the fit column checks every row against it. Weights marked “file” use the real GGUF download size; “est.” rows are computed from the parameter count.
How to pick a quant
Take the biggest quant that fits with room left for context. Q4_K_M is the usual sweet spot. Below Q4 quality drops fast, above Q6 you mostly pay memory for nothing. Big models (70B+, large MoE) tolerate low quants better than small ones.
- LosslessF16, Q8_0
- Near-losslessQ6_K, Q5_K_M
- Small lossQ5_K_S, Q4_K_M, IQ4_NL, IQ4_XS, Q4_K_S
- Noticeable lossQ4_0, Q3_K_L, Q3_K_M, IQ3_M
- Heavy lossIQ3_XXS, Q3_K_S, IQ2_M, Q2_K
Typical quality loss, not measured per model. Tiers come from KL divergence against FP16 on Llama 3 8B: llama.cpp perplexity README: LLaMA 3 8B scoreboard (KLD and ΔPPL vs FP16, Wikitext-2); llama.cpp quantize tool: ΔPPL per quant type @ Llama-3-8B
How much context fits?
At 8K context, Q4_K_M needs ≈108 GB(102 GB weights + 0.8 GB KV cache + 5.6 GB overhead). Pick a GPU above to see how much context fits.
Weights + overheadKV cache
Can the Apple M2 Ultra (192 GB) run Qwen3.8-Flash-Next? →
Speed vs quality per quant
Smaller quants run faster and fit in less memory, but lose quality.
Fits in VRAMTight fitCPU offload✕ won't runQuality is typical KL divergence vs FP16, not measured for this model.
Real-world speed of Qwen3.8-Flash-Next
Tokens per second measured by people running it at home. A GPU shows a median once 3 reports agree on the same setup. Reports far from our estimate wait for a review. Measure yours with llama-bench →
No medians yet. Be one of the first 3 to report a setup.
All reports
Run Qwen3.8-Flash-Next locally
--quantQ4_K_Mdefault; pick your GPU to tailor itunsloth/Qwen3.8-Flash-Next-GGUF
ollama run qwen3.8-flash-nextThe library build picks its own default quantisation.
ollama run hf.co/unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL llama-server -hf unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XLDownloads the GGUF on first run. Installed through llama.app? The same flags work with `llama serve`.
lms get unsloth/Qwen3.8-Flash-Next-GGUF@UD-Q4_K_XLThen load it from the LM Studio app or with `lms load`.
vllm serve Qwen/Qwen3.8-Flash-Next vllm serve Qwen/Qwen3.8-Flash-Next-FP8services:
vllm:
image: vllm/vllm-openai:latest
command: Qwen/Qwen3.8-Flash-Next
ports:
- "8000:8000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 8000.
sglang serve Qwen/Qwen3.8-Flash-Next --host 0.0.0.0 --port 30000services:
sglang:
image: lmsysorg/sglang:latest
command: sglang serve Qwen/Qwen3.8-Flash-Next --host 0.0.0.0 --port 30000
ports:
- "30000:30000"
ipc: host
volumes:
- ~/.cache/huggingface:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]API on port 30000.
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="Qwen/Qwen3.8-Flash-Next", dtype="auto", device_map="auto")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
{"type": "text", "text": "Describe this image."},
],
}
]
out = pipe(text=messages, max_new_tokens=256)
print(out[0]["generated_text"][-1]["content"])Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 91.7% | self-reported |
| Humanity's Last Exam | 35.9% | self-reported |
| SWE-bench Pro | 62.5% | self-reported |
| SWE-bench Multilingual | 81.0% | self-reported |
| LMArena WebDev | 1633 | independent |
Self-reported scores come from the model card and are not independently verified. Rank is among all models with a score on that benchmark.
Quantised versions and downloads
| Repository | Format | Quant | Size |
|---|---|---|---|
| RadixArk/Qwen3.8-Flash-Next-NVFP4 | Safetensors | NVFP4 | — |
| nvidia/Qwen3.8-Flash-Next-NVFP4 | Safetensors | NVFP4 | — |
| Qwen/Qwen3.8-Flash-Next-FP8 | Safetensors | FP8 | — |
| unsloth/Qwen3.8-Flash-Next-GGUF | GGUF | UD-IQ1_S | 73 GB |
| unsloth/Qwen3.8-Flash-Next-GGUF | GGUF | UD-IQ1_M | 75 GB |
| unsloth/Qwen3.8-Flash-Next-GGUF | GGUF | UD-Q2_K_XL | 79 GB |
| unsloth/Qwen3.8-Flash-Next-GGUF | GGUF | UD-IQ3_XXS | 82 GB |
| unsloth/Qwen3.8-Flash-Next-GGUF | GGUF | UD-Q3_K_XL | 90 GB |
| unsloth/Qwen3.8-Flash-Next-GGUF | GGUF | UD-IQ4_XS | 94 GB |
| unsloth/Qwen3.8-Flash-Next-GGUF | GGUF | UD-Q4_K_XL | 111 GB |
About Qwen3.8-Flash-Next
As the frontier of foundation models pushes toward ever-larger parameter counts and ever-longer context windows, the question is no longer just how much we can scale, but how efficiently we can do so. Sustainable progress toward artificial general intelligence (AGI) that benefits everyone demands architectural innovation. Today, we are sharing a concrete step in that direction: Qwen3.8-Flash-Next. This experimental preview of the architecture that will underpin Qwen4 is built around a fundamental rethinking of how the core components of modern large language models (LLMs) interact at scale. The first open-weight release under this architecture is Qwen3.8-Flash-Next, which introduces:
Full model card on Hugging Face →Alternatives to Qwen3.8-Flash-Next
All alternatives →Inkling-Small is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages.
MiniMax-M3.1-Flash is a native multimodal mixture-of-experts model for coding, agentic workflows, computer use, and cybersecurity. It supports text, image, and video inputs with a context window of up to 1M tokens.
Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 is the full-precision release of NVIDIA Nemotron 3.5 Super VL, a vision-language model for reasoning, coding, tool use, document understanding, and video understanding.
Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
Qwen3.8-Flash-Next FAQ
- How much VRAM does Qwen3.8-Flash-Next need?
- About 108 GB at Q4_K_M with an 8K context. Q8_0 needs about 188 GB and full precision about 353 GB. Longer contexts need more memory for the KV cache.
- Can Qwen3.8-Flash-Next run on the Apple M2 Ultra (192 GB)?
- Yes. It fits at Q5_K_M (about 126 GB), at an estimated 10 tokens/s. It fits comfortably on the Apple M3 Ultra (512 GB).
- Can I use Qwen3.8-Flash-Next commercially?
- Yes, with conditions. It is released under qwen-community-1.0. Custom licence: read the model card before using it commercially.
- What is the context length of Qwen3.8-Flash-Next?
- 262,144 tokens (256K). The full window needs far more memory than an 8K context.
- How do I run Qwen3.8-Flash-Next with Ollama or llama.cpp?
- With Ollama: ollama run qwen3.8-flash-next. With llama.cpp: llama-server -hf unsloth/Qwen3.8-Flash-Next-GGUF:UD-Q4_K_XL, which starts an OpenAI-compatible server.
Rate this model
Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.
0 comments