No — not on this device

Qwen3.8-Flash-Next 180B-A6B at Q4_K_M needs 102.0 GB against 96.0 GB usable, and the shortfall of 6.0 GB is more than 16 GB of system RAM can cover at a tolerable speed. A smaller sibling or a lower quantisation is the honest answer here.

Does not fit 8K context Q4_K_M · 101.2 GB Qwen Community 1.0 Released 24 Aug 2026 Vision

The open preview of the Qwen4 architecture: a 125B-A6B hybrid (Gated DeltaNet + sparse attention, KV cache on 12 of 48 blocks) plus a 51B n-gram embedding and a 4B draft head — 180B on disk, 6B active. The hosted "Qwen3.8-Flash" is this model with a 1M window.

Hardware requirements What hardware do I need to run Qwen3.8-Flash-Next 180B-A6B? →

At Q4_K_M with an 8K context: a 141 GB GPU (H200 SXM) or a 192 GB Mac (M2 Ultra). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

Fits instead: Qwen3.8 27B (16.7 GB)

The VRAM budget

weights 101.2 GB
Weights 101.2 GB KV cache @ 8K 0.19 GB Runtime overhead 0.6 GB Over budget 6.0 GB past 96.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 178.1 GB 178.9 GB — ~12 −0.1% ppl 82.9 GB over
Q6_K 137.5 GB 138.3 GB — ~16 −0.4% ppl 42.3 GB over
Q5_K_M 118.8 GB 119.6 GB — ~18 −0.8% ppl 23.6 GB over
Q4_K_M 101.2 GB 102.0 GB — ~21 −1.9% ppl 6.0 GB over
Q3_K_M 81.9 GB 82.7 GB 256K 26 −5.4% ppl Long context
Q2_K 70.2 GB 71.0 GB 256K 30 −15% ppl Long context

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. Only 12 of its 48 blocks keep a per-token KV cache; the rest are linear-attention, Mamba or convolution blocks with a fixed-size state.

How to run it

terminal
$ llama-server \
    -hf Qwen/Qwen3.8-Flash-Next:Q4_K_M \
    -c 8192 -ngl 45

The engine underneath most of the others. Every knob is exposed. More on llama.cpp.

01Download is 101.2 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02The GPU shares one pool with the operating system, and these numbers count about 96.0 GB of 128 GB as its share. Under Linux the GPU can usually address more than that, so treat the verdict as conservative.
03If it falls back to CPU silently, drop the context first, then step down a quantisation.
See all models for this rig Compare with another model

Related models on a DGX Spark · 128 GB

ModelTotalTok/s est.
Qwen3.8 27B
27.8B · same family
Q4_K_M · 16.7 GB 9.8 Runs great
Qwen3.8 2.4T-A95B
2446B MoE · same family
Q4_K_M · 1376.7 GB — Won't fit
Qwen3 235B-A22B
235B MoE · similar size
Q4_K_M · 134.2 GB — Won't fit
Qwen3.5 122B-A10B
125B MoE · similar size
Q4_K_M · 71.1 GB 13 Runs great
Nemotron 3 Super 120B-A12B
124B MoE · similar size
Q4_K_M · 70.4 GB 11 Runs great
Ling 3.0 Flash 124B-A5B
124B MoE · similar size
Q4_K_M · 70.4 GB 25 Runs great
Mistral Small 4 119B-A6B
119B MoE · similar size
Q4_K_M · 67.7 GB 19 Runs great

Every model against the DGX Spark · 128 GB →

Qwen3.8-Flash-Next 180B-A6B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
102.0 GB — Won't fit
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
102.0 GB — Won't fit
M4 · 16 GB
10.7 GB usable · 120 GB/s
102.0 GB — Won't fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
102.0 GB — Won't fit
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
102.0 GB — Won't fit
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
102.0 GB — Won't fit
H200 SXM
139.4 GB usable · 4800 GB/s
102.0 GB 331 Runs great
M2 Ultra · 192 GB
144.0 GB usable · 800 GB/s
102.0 GB 62 Runs great

All 114 devices, by tier →