Q4_K_M: Smooth Fit 7.94 GB / 15.2 GB Usable
Qwen3-8B on 摩尔线程 MTT S80 16GB: VRAM Requirement & Speed Estimate
Yes. At Q4_K_M 4-bit quantization with a 16K context window, Qwen3-8B requires 7.94 GB of VRAM (4.97 GB weights + 2.42 GB KV cache + 0.55 GB overhead), fitting within 摩尔线程 S80 16G's 15.2 GB usable memory at ~52.2 tokens/s.
Concurrency (Batch):
Dense 8.2B·36L (d=4096)·32Q/8KV·Ctx 128K
Smooth Fit7.94 / 15.2 GB~52.2 tok/s· Q4_K_M · 16K ctx
3. Weight Quantization
4. Per-Request Context16K (16,384 tok)
Verified: 2026-11-20·Roofline bandwidth/compute estimate (Batch=1)
Smooth Fit
7.94/ 15.2 GB usable
Physical 16 GB · Load 52.2%
Theoretical Decode Speed
~52.2tokens/s
Actual speed varies ~±25% by runtime
Max Context at Batch=1
64K/ 128K
Enable Q8/Q4 KV quantization to scale batch concurrency
Weights: 4.97 GBKV Cache (1×16K): 2.42 GBOverhead: 0.55 GB
🏃 Smooth & Snappy~9.6s for a 500-token response