Alibaba Cloud180B (6B active)~109 GB VRAM at Q4_K_M

Qwen3.8-Flash-Next — VRAM, speed & local setup

Written by Jakub Rusinowski · Last updated

An experimental preview of the architecture intended to underpin Qwen4, not a conventional production release. 180B of parameters must be resident — a 125B MoE backbone, a 51B n-gram lookup table and a 4B multi-token-prediction head, about 109 GB at Q4_K_M — while only 6B activate per token. 48 layers alternating three Gated DeltaNet blocks (compressing history into a fixed recurrent state) with one Qwen Sparse Attention block (precise long-range retrieval). Natively multimodal, 262,144-token context extensible to 1M via YaRN. Qwen Community License 1.0, NOT the Apache 2.0 the 27B carries.

Qwen3.8-Flash-Next needs about 109 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Logic89
Creative84
Coding90

VRAM and speed by quantization

Quoted against NVIDIA RTX 4090 (24 GB). Includes the KV cache at 8K context, so it reads higher than the headline figure.

QuantVRAMSpeed (est.)Fit
Q2_K
2.63 bpw
60.2 GB—Too big
Q3_K_M
3.41 bpw
77.7 GB—Too big
Q4_K_M
4.83 bpw
109.7 GB—Too big
Q5_K_M
5.67 bpw
128.6 GB—Too big
Q6_K
6.56 bpw
148.6 GB—Too big
Q8_0
8.50 bpw
192.3 GB—Too big
F16
16.00 bpw
361 GB—Too big

Black marker = usable memory on the NVIDIA RTX 4090 (24 GB). Estimates from the memory-bandwidth roofline on the methodology page. Qwen3.8-Flash-Next VRAM calculator →

Get Qwen3.8-Flash-Next running

The cheapest catalogued GPU that runs Qwen3.8-Flash-Next is the NVIDIA DGX Spark (128 GB).

Buy this hardware NVIDIA DGX Spark (128GB) — 128 GB VRAM · 150 W board powerDeploy in the cloud now RunPod

or compare on Vast.ai

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
NVIDIA DGX Spark (128GB)
128 GB VRAM · 150 W board power
2026 prices are volatile — check the current listing.

How to run Qwen3.8-Flash-Next

Install Ollama, then run:

ollama run qwen3-8
Weights on Hugging Face: Qwen/Qwen3.8-Flash-Next ↗

Specifications

Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.

Parameters
180 Billion (6B active)
Context window
262,144
Architecture
Gated DeltaNet + Qwen Sparse Attention MoE
Provider
Alibaba Cloud
Licence
Qwen Community License 1.0
Practical deployment
Workstation (large unified memory or pro GPU)
Specified at
Q4_K_M
System RAM
192 GB
Record updated
2026-09-11
LicenceQwen Community License 1.0Commercial use permitted

Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.

Above 100M monthly active users or $20M monthly revenue, an attribution duty applies; model-as-a-service resale needs a separate agreement.

Quality and use cases

Scores as published by the model’s authors or an independent evaluator — quality, not throughput, and not measured by us.

Best forresearchagentic codinglong contextmultimodal

Can I run Qwen3.8-Flash-Next on my GPU?

Other Qwen3.8 sizes

Qwen3.8-Flash-Next — frequently asked questions

How much VRAM does Qwen3.8-Flash-Next need?

About 109 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does Qwen3.8-Flash-Next run on an RTX 4090 (24 GB)?

No. Qwen3.8-Flash-Next needs about 109 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.

How do I run Qwen3.8-Flash-Next locally?

Install Ollama and run `ollama run qwen3-8`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does Qwen3.8 come in?

Qwen3.8 27B (18 GB), Qwen3.8-Max (1450 GB), Qwen3.8-Flash-Next (109 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.