Qwen3 8B hardware requirements

About the model

Parameters
8.2B
Attention
Full attention
Max context
32,768 tokens
Released
2025-04-29

GGUF files

Tracked quantizations of Qwen3 8B, smallest first
QuantFile sizeQualityPublished by
Q2_K3.28 GBHeavy lossCommunity GGUF · unsloth
IQ4_XS4.58 GBGood balanceCommunity GGUF · unsloth
Q4_K_Mbaseline5.03 GBGood balanceCommunity GGUF · unsloth
Q8_08.71 GBNear-losslessCommunity GGUF · unsloth

Some repositories publish only Unsloth Dynamic (UD) variants; sizes are those of the file you would download.

Memory needed by quant and context

Weights + f16 KV cache + compute buffer, in GB. Add about 0.6 GB if the GPU also drives your display on Windows.
Quant4k8k16k32k
Q2_K4.45.16.38.9
IQ4_XS5.76.47.610.2
Q4_K_M6.26.88.110.7
Q8_09.910.511.814.3

Which GPUs can run Qwen3 8B?

How to read the verdicts

Runs great
Fully on the GPU at 20 tok/s or more
Runs well
Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
Runs slowly
2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
Won't run
Does not fit, or under 2 tok/s

Scroll sideways to see every column.

54 GPUs, Macs and CPU setups at Q4_K_M with 8k context, sorted by verdict and speed
HardwareVerdictSpeedQuantMemoryRuns asContextNotesPrice
GeForce RTX 5090
Runs great
est. 201.1 tok/s177.0–225.2calibrated estimate ±12%
Q4_K_M7.4 / 32.0 GBFull GPUup to 32k—$4,200 street (as of 2026-08-09)
Radeon RX 7900 XTX
Runs great
est. 120.0 tok/s105.6–134.4calibrated estimate ±12%
Q4_K_M7.4 / 24.0 GBFull GPUup to 32k—$999 launch MSRP
GeForce RTX 3090 Ti
Runs great
est. 113.1 tok/s99.5–126.7calibrated estimate ±12%
Q4_K_M7.4 / 24.0 GBFull GPUup to 32k—$1,999 launch MSRP
GeForce RTX 4090
Runs great
est. 113.1 tok/s99.5–126.7calibrated estimate ±12%
Q4_K_M7.4 / 24.0 GBFull GPUup to 32k—$2,755 street (as of 2026-08-09)
GeForce RTX 5080
Runs great
est. 107.7 tok/s94.8–120.7calibrated estimate ±12%
Q4_K_M7.4 / 16.0 GBFull GPUup to 32k—$1,256 street (as of 2026-08-09)
GeForce RTX 3090
Runs great
est. 105.0 tok/s92.4–117.6calibrated estimate ±12%
Q4_K_M7.4 / 24.0 GBFull GPUup to 32k—$1,050 street (as of 2026-08-09)
GeForce RTX 3080 12GB
Runs great
est. 102.3 tok/s90.1–114.6calibrated estimate ±12%
Q4_K_M7.4 / 12.0 GBFull GPUup to 32k—$799 launch MSRP
GeForce RTX 5070 Ti
Runs great
est. 100.5 tok/s88.5–112.6calibrated estimate ±12%
Q4_K_M7.4 / 16.0 GBFull GPUup to 32k—$949 street (as of 2026-08-09)
GeForce RTX 5080 Laptop
Runs great
est. 100.5 tok/s88.5–112.6calibrated estimate ±12%
Q4_K_M7.4 / 16.0 GBFull GPUup to 32k——
GeForce RTX 5090 Laptop
Runs great
est. 100.5 tok/s88.5–112.6calibrated estimate ±12%
Q4_K_M7.4 / 24.0 GBFull GPUup to 32k——
Radeon RX 7900 XT
Runs great
est. 100.0 tok/s88.0–112.0calibrated estimate ±12%
Q4_K_M7.4 / 20.0 GBFull GPUup to 32k—$899 launch MSRP
GeForce RTX 3080 10GB
Runs great
est. 85.3 tok/s75.1–95.5calibrated estimate ±12%
Q4_K_M7.4 / 10.0 GBFull GPUup to 16k—$699 launch MSRP
GeForce RTX 4080 Super
Runs great
est. 82.6 tok/s72.7–92.5calibrated estimate ±12%
Q4_K_M7.4 / 16.0 GBFull GPUup to 32k—$999 launch MSRP
Radeon RX 9070
Runs great
est. 80.7 tok/s71.0–90.3calibrated estimate ±12%
Q4_K_M7.4 / 16.0 GBFull GPUup to 32k—$639 street (as of 2026-08-09)
Radeon RX 9070 XT
Runs great
est. 80.7 tok/s71.0–90.3calibrated estimate ±12%
Q4_K_M7.4 / 16.0 GBFull GPUup to 32k—$689 street (as of 2026-08-09)
GeForce RTX 4080
Runs great
est. 80.5 tok/s70.8–90.1calibrated estimate ±12%
Q4_K_M7.4 / 16.0 GBFull GPUup to 32k—$1,199 launch MSRP
Radeon RX 7800 XT
Runs great
est. 78.0 tok/s68.7–87.4calibrated estimate ±12%
Q4_K_M7.4 / 16.0 GBFull GPUup to 32k—$499 launch MSRP
GeForce RTX 4070 Ti Super
Runs great
est. 75.4 tok/s66.4–84.5calibrated estimate ±12%
Q4_K_M7.4 / 16.0 GBFull GPUup to 32k—$799 launch MSRP
GeForce RTX 5070
Runs great
est. 75.4 tok/s66.4–84.5calibrated estimate ±12%
Q4_K_M7.4 / 12.0 GBFull GPUup to 32k—$629 street (as of 2026-08-09)
GeForce RTX 5070 Ti Laptop
Runs great
est. 75.4 tok/s66.4–84.5calibrated estimate ±12%
Q4_K_M7.4 / 12.0 GBFull GPUup to 32k——
GeForce RTX 2080 Ti
Runs great
est. 69.1 tok/s60.8–77.4calibrated estimate ±12%
Q4_K_M7.4 / 11.0 GBFull GPUup to 16k—$999 launch MSRP
GeForce RTX 4090 Laptop
Runs great
est. 64.6 tok/s56.9–72.4calibrated estimate ±12%
Q4_K_M7.4 / 16.0 GBFull GPUup to 32k——
Apple M5 Max (40-core GPU) · 48 GB
Runs great
est. 59.1 tok/s47.2–70.9calibrated estimate ±20%
Q4_K_M6.8 / 33.6 GBUnified memoryup to 32k——
Apple M3 Ultra · 96 GB
Runs great
est. 57.8 tok/s46.2–69.3calibrated estimate ±20%
Q4_K_M6.8 / 67.2 GBUnified memoryup to 32k——
GeForce RTX 4070
Runs great
est. 56.6 tok/s49.8–63.3calibrated estimate ±12%
Q4_K_M7.4 / 12.0 GBFull GPUup to 32k—$599 launch MSRP
GeForce RTX 4070 Super
Runs great
est. 56.6 tok/s49.8–63.3calibrated estimate ±12%
Q4_K_M7.4 / 12.0 GBFull GPUup to 32k—$599 launch MSRP
Apple M2 Ultra · 64 GB
Runs great
est. 56.4 tok/s45.1–67.7calibrated estimate ±20%
Q4_K_M6.8 / 44.8 GBUnified memoryup to 32k——
GeForce GTX 1080 Ti
Runs great
est. 54.3 tok/s38.0–70.6theoretical estimate ±30%
Q4_K_M7.4 / 11.0 GBFull GPUup to 16k—$699 launch MSRP
Apple M4 Max (40-core GPU) · 48 GB
Runs great
est. 52.5 tok/s42.0–63.0calibrated estimate ±20%
Q4_K_M6.8 / 33.6 GBUnified memoryup to 32k——
GeForce RTX 3070
Runs great
est. 50.3 tok/s44.2–56.3calibrated estimate ±12%
Q4_K_M7.4 / 8.0 GBFull GPUup to 8k—$499 launch MSRP
GeForce RTX 5060
Runs great
est. 50.3 tok/s44.2–56.3calibrated estimate ±12%
Q4_K_M7.4 / 8.0 GBFull GPUup to 8k—$339 street (as of 2026-08-09)
GeForce RTX 5060 Ti 16GB
Runs great
est. 50.3 tok/s44.2–56.3calibrated estimate ±12%
Q4_K_M7.4 / 16.0 GBFull GPUup to 32k—$569 street (as of 2026-08-09)
GeForce RTX 5060 Ti 8GB
Runs great
est. 50.3 tok/s44.2–56.3calibrated estimate ±12%
Q4_K_M7.4 / 8.0 GBFull GPUup to 8k—$429 street (as of 2026-08-09)
GeForce RTX 4080 Laptop
Runs great
est. 48.5 tok/s42.7–54.3calibrated estimate ±12%
Q4_K_M7.4 / 12.0 GBFull GPUup to 32k——
Apple M5 Max (32-core GPU) · 36 GB
Runs great
est. 44.2 tok/s35.4–53.1calibrated estimate ±20%
Q4_K_M6.8 / 25.2 GBUnified memoryup to 32k——
Intel Arc B580
Runs great
est. 43.1 tok/s34.5–51.8calibrated estimate ±20%
Q4_K_M7.4 / 12.0 GBFull GPUup to 32k—$290 street (as of 2026-08-09)
GeForce RTX 3060 12GB
Runs great
est. 40.4 tok/s35.6–45.2calibrated estimate ±12%
Q4_K_M7.4 / 12.0 GBFull GPUup to 32k—$250 street (as of 2026-08-09)
Radeon RX 9060 XT 16GB
Runs great
est. 40.3 tok/s35.4–45.1calibrated estimate ±12%
Q4_K_M7.4 / 16.0 GBFull GPUup to 32k—$449 street (as of 2026-08-09)
Apple M4 Max (32-core GPU) · 36 GB
Runs great
est. 39.4 tok/s31.5–47.3calibrated estimate ±20%
Q4_K_M6.8 / 25.2 GBUnified memoryup to 32k——
GeForce RTX 4060 Ti 16GB
Runs great
est. 32.3 tok/s28.4–36.2calibrated estimate ±12%
Q4_K_M7.4 / 16.0 GBFull GPUup to 32k—$499 launch MSRP
GeForce RTX 4060 Ti 8GB
Runs great
est. 32.3 tok/s28.4–36.2calibrated estimate ±12%
Q4_K_M7.4 / 8.0 GBFull GPUup to 8k—$399 launch MSRP
GeForce RTX 4060
Runs great
est. 30.5 tok/s26.9–34.2calibrated estimate ±12%
Q4_K_M7.4 / 8.0 GBFull GPUup to 8k—$299 launch MSRP
Apple M5 Pro · 24 GB
Runs great
est. 29.5 tok/s23.6–35.4calibrated estimate ±20%
Q4_K_M6.8 / 16.8 GBUnified memoryup to 16k——
GeForce RTX 4060 Laptop
Runs great
est. 28.7 tok/s25.3–32.2calibrated estimate ±12%
Q4_K_M7.4 / 8.0 GBFull GPUup to 8k——
GeForce RTX 4070 Laptop
Runs great
est. 28.7 tok/s25.3–32.2calibrated estimate ±12%
Q4_K_M7.4 / 8.0 GBFull GPUup to 8k——
Ryzen AI Max+ 395 (Strix Halo) · 32 GB
Runs great
est. 26.7 tok/s21.3–32.0calibrated estimate ±20%
Q4_K_M6.8 / 22.4 GBUnified memoryup to 16k—$1,999 launch MSRP
Apple M4 Pro · 24 GB
Runs great
est. 26.3 tok/s21.0–31.5calibrated estimate ±20%
Q4_K_M6.8 / 16.8 GBUnified memoryup to 16k——
GeForce RTX 3050 8GB
Runs great
est. 25.1 tok/s22.1–28.2calibrated estimate ±12%
Q4_K_M7.4 / 8.0 GBFull GPUup to 8k—$249 launch MSRP
NVIDIA DGX Spark · 128 GB
Runs well
est. 17.5 tok/s14.0–21.0calibrated estimate ±20%
Q4_K_M6.8 / 89.6 GBUnified memoryup to 32k
  • Q2_K (heavy quality loss): Runs great
$3,999 launch MSRP
Apple M5 · 16 GB
Runs well
est. 14.8 tok/s11.8–17.7calibrated estimate ±20%
Q4_K_M6.8 / 11.2 GBUnified memoryup to 32k
  • Q2_K (heavy quality loss): Runs great
—
Apple M4 · 16 GB
Runs well
est. 11.5 tok/s9.2–13.9calibrated estimate ±20%
Q4_K_M6.8 / 11.2 GBUnified memoryup to 16k——
DDR5-6000 dual-channel CPU · 16 GB
Runs slowly
est. 7.7 tok/s6.2–9.2calibrated estimate ±20%
Q4_K_M6.2 GB RAMCPU onlyup to 32k——
DDR5-5600 dual-channel CPU · 16 GB
Runs slowly
est. 7.2 tok/s5.7–8.6calibrated estimate ±20%
Q4_K_M6.2 GB RAMCPU onlyup to 32k——
DDR4-3200 dual-channel CPU · 16 GB
Runs slowly
est. 4.1 tok/s3.3–4.9calibrated estimate ±20%
Q4_K_M6.2 GB RAMCPU onlyup to 32k——

Cheapest GPUs that run it

  • Runs greatGeForce RTX 3060 12GB$250 street (as of 2026-08-09), est. 40.4 tok/s (35.6–45.2, calibrated estimate ±12%).

Measured results for Qwen3 8B

Public benchmarks we calibrate against. Their conditions (context, backend, flags) can differ from the estimates above.

Measured results for Qwen3 8B
HardwareQuantBackendContextPrompt (tok/s)Generation (tok/s)FlagsSourceMeasured
GeForce RTX 5090Q4_K_XLllama.cpp16k—145.3—hardware-corner.net2026-08-09
GeForce RTX 4090Q4_K_XLllama.cpp16k—104.3—hardware-corner.net2026-08-09
GeForce RTX 3090Q4_K_XLllama.cpp16k—87.5—hardware-corner.net2026-08-09
GeForce RTX 3060 12GBQ4_K_XLllama.cpp16k—42.0—hardware-corner.net2026-08-09

Frequently asked questions

How much VRAM does Qwen3 8B need?

At Q4_K_M the weights are 5.03 GB; with 8k context the total is about 6.8 GB (KV cache 1.2 GB, compute buffer 0.6 GB). The smallest tracked file (Q2_K (heavy quality loss)) needs about 5.1 GB.

What is the cheapest GPU that runs Qwen3 8B well?

Cheapest that runs it great: GeForce RTX 3060 12GB at $250 (street price as of 2026-08-09), est. 40.4 tok/s (35.6–45.2, calibrated estimate ±12%).

Can Qwen3 8B run on an 8 GB, 16 GB or 24 GB GPU?

At Q4_K_M with 8k context: GeForce RTX 4060 — Runs great, est. 30.5 tok/s (26.9–34.2, calibrated estimate ±12%); GeForce RTX 5060 Ti 16GB — Runs great, est. 50.3 tok/s (44.2–56.3, calibrated estimate ±12%); GeForce RTX 3090 — Runs great, est. 105.0 tok/s (92.4–117.6, calibrated estimate ±12%).

Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.