NVIDIA · 48 GB GDDR6 · 768 GB/s bandwidth ·
Alibaba · 79.7B (active 3B) · MoE · model ctx up to 256K
Yes — the RTX A6000 48GB (48 GB GDDR6) can run Qwen3-Coder-Next. At Q4 with the default 8K context it needs ≈ 45.44 GB VRAM (weights 43.84 GB + KV cache 0.6 GB + 1 GB runtime overhead), which fits within 48 GB. Decode at Q4/8K: ≈ 162.9 tok/s (estimated, batch 1). FP16 needs ≈ 161.0 GB — does not fit on this card. Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology.
Fit & speed by quant and context
Quant
Context
VRAM needed
Fits?
tok/s (decode)
Q4
4K
45.14 GB
Yes
162.9est.
Q4
8K default
45.44 GB
Yes
162.9est.
Q4
32K
47.24 GB
No
480.6est.
FP16
4K
160.7 GB
No
11.4est.
FP16
8K default
161.0 GB
No
11.4est.
FP16
32K
162.8 GB
No
11.1est.
Fits = weights + KV(ctx) + 1 GB overhead ≤ 95% of VRAM. Measured
anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s
means the model is far beyond this card (offload-only territory).