Qwen3 14B hardware requirements
About the model
- Parameters
- 14.8B
- Attention
- Full attention
- Max context
- 32,768 tokens
- Released
- 2025-04-29
- Model card
- Qwen3 14B on Hugging Face
GGUF files
| Quant | File size | Quality | Published by |
|---|---|---|---|
| Q2_K | 5.75 GB | Heavy loss | Community GGUF · unsloth |
| IQ4_XS | 8.14 GB | Good balance | Community GGUF · unsloth |
| Q4_K_Mbaseline | 9.00 GB | Good balance | Community GGUF · unsloth |
| Q8_0 | 15.70 GB | Near-lossless | Community 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
| Quant | 4k | 8k | 16k | 32k |
|---|---|---|---|---|
| Q2_K | 7.0 | 7.7 | 9.1 | 11.9 |
| IQ4_XS | 9.3 | 10.1 | 11.5 | 14.3 |
| Q4_K_M | 10.2 | 10.9 | 12.3 | 15.2 |
| Q8_0 | 16.9 | 17.6 | 19.0 | 21.9 |
Which GPUs can run Qwen3 14B?
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
Dense models split between GPU and CPU slow down sharply — the CPU side sets the pace. MoE models that keep only their experts in system RAM degrade far more gently.
Scroll sideways to see every column.
| Hardware | Verdict | Speed | Quant | Memory | Runs as | Context | Notes | Price |
|---|---|---|---|---|---|---|---|---|
| GeForce RTX 5090 | Runs greatDetails | est. 121.3 tok/s106.7–135.8calibrated estimate ±12% | Q4_K_M | 11.5 / 32.0 GB | Full GPU | up to 32k | — | $4,200 street (as of 2026-08-09) |
| Radeon RX 7900 XTX | Runs great | est. 72.4 tok/s63.7–81.1calibrated estimate ±12% | Q4_K_M | 11.5 / 24.0 GB | Full GPU | up to 32k | — | $999 launch MSRP |
| GeForce RTX 3090 Ti | Runs great | est. 68.2 tok/s60.0–76.4calibrated estimate ±12% | Q4_K_M | 11.5 / 24.0 GB | Full GPU | up to 32k | — | $1,999 launch MSRP |
| GeForce RTX 4090 | Runs greatDetails | est. 68.2 tok/s60.0–76.4calibrated estimate ±12% | Q4_K_M | 11.5 / 24.0 GB | Full GPU | up to 32k | — | $2,755 street (as of 2026-08-09) |
| GeForce RTX 5080 | Runs great | est. 65.0 tok/s57.2–72.8calibrated estimate ±12% | Q4_K_M | 11.5 / 16.0 GB | Full GPU | up to 32k | — | $1,256 street (as of 2026-08-09) |
| GeForce RTX 3090 | Runs greatDetails | est. 63.4 tok/s55.7–71.0calibrated estimate ±12% | Q4_K_M | 11.5 / 24.0 GB | Full GPU | up to 32k | — | $1,050 street (as of 2026-08-09) |
| GeForce RTX 3080 12GB | Runs great | est. 61.7 tok/s54.3–69.1calibrated estimate ±12% | Q4_K_M | 11.5 / 12.0 GB | Full GPU | up to 8k | — | $799 launch MSRP |
| GeForce RTX 5070 Ti | Runs great | est. 60.6 tok/s53.4–67.9calibrated estimate ±12% | Q4_K_M | 11.5 / 16.0 GB | Full GPU | up to 32k | — | $949 street (as of 2026-08-09) |
| GeForce RTX 5080 Laptop | Runs great | est. 60.6 tok/s53.4–67.9calibrated estimate ±12% | Q4_K_M | 11.5 / 16.0 GB | Full GPU | up to 32k | — | — |
| GeForce RTX 5090 Laptop | Runs great | est. 60.6 tok/s53.4–67.9calibrated estimate ±12% | Q4_K_M | 11.5 / 24.0 GB | Full GPU | up to 32k | — | — |
| Radeon RX 7900 XT | Runs great | est. 60.3 tok/s53.1–67.6calibrated estimate ±12% | Q4_K_M | 11.5 / 20.0 GB | Full GPU | up to 32k | — | $899 launch MSRP |
| GeForce RTX 4080 Super | Runs great | est. 49.8 tok/s43.8–55.8calibrated estimate ±12% | Q4_K_M | 11.5 / 16.0 GB | Full GPU | up to 32k | — | $999 launch MSRP |
| Radeon RX 9070 | Runs great | est. 48.6 tok/s42.8–54.5calibrated estimate ±12% | Q4_K_M | 11.5 / 16.0 GB | Full GPU | up to 32k | — | $639 street (as of 2026-08-09) |
| Radeon RX 9070 XT | Runs great | est. 48.6 tok/s42.8–54.5calibrated estimate ±12% | Q4_K_M | 11.5 / 16.0 GB | Full GPU | up to 32k | — | $689 street (as of 2026-08-09) |
| GeForce RTX 4080 | Runs great | est. 48.5 tok/s42.7–54.4calibrated estimate ±12% | Q4_K_M | 11.5 / 16.0 GB | Full GPU | up to 32k | — | $1,199 launch MSRP |
| Radeon RX 7800 XT | Runs great | est. 47.1 tok/s41.4–52.7calibrated estimate ±12% | Q4_K_M | 11.5 / 16.0 GB | Full GPU | up to 32k | — | $499 launch MSRP |
| GeForce RTX 4070 Ti Super | Runs great | est. 45.5 tok/s40.0–50.9calibrated estimate ±12% | Q4_K_M | 11.5 / 16.0 GB | Full GPU | up to 32k | — | $799 launch MSRP |
| GeForce RTX 5070 | Runs greatDetails | est. 45.5 tok/s40.0–50.9calibrated estimate ±12% | Q4_K_M | 11.5 / 12.0 GB | Full GPU | up to 8k | — | $629 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti Laptop | Runs great | est. 45.5 tok/s40.0–50.9calibrated estimate ±12% | Q4_K_M | 11.5 / 12.0 GB | Full GPU | up to 8k | — | — |
| GeForce RTX 4090 Laptop | Runs great | est. 39.0 tok/s34.3–43.7calibrated estimate ±12% | Q4_K_M | 11.5 / 16.0 GB | Full GPU | up to 32k | — | — |
| Apple M5 Max (40-core GPU) · 48 GB | Runs great | est. 35.6 tok/s28.5–42.7calibrated estimate ±20% | Q4_K_M | 10.9 / 33.6 GB | Unified memory | up to 32k | — | — |
| Apple M3 Ultra · 96 GB | Runs great | est. 34.8 tok/s27.9–41.8calibrated estimate ±20% | Q4_K_M | 10.9 / 67.2 GB | Unified memory | up to 32k | — | — |
| GeForce RTX 4070 | Runs greatDetails | est. 34.1 tok/s30.0–38.2calibrated estimate ±12% | Q4_K_M | 11.5 / 12.0 GB | Full GPU | up to 8k | — | $599 launch MSRP |
| GeForce RTX 4070 Super | Runs great | est. 34.1 tok/s30.0–38.2calibrated estimate ±12% | Q4_K_M | 11.5 / 12.0 GB | Full GPU | up to 8k | — | $599 launch MSRP |
| Apple M2 Ultra · 64 GB | Runs great | est. 34.0 tok/s27.2–40.8calibrated estimate ±20% | Q4_K_M | 10.9 / 44.8 GB | Unified memory | up to 32k | — | — |
| Apple M4 Max (40-core GPU) · 48 GB | Runs great | est. 31.7 tok/s25.3–38.0calibrated estimate ±20% | Q4_K_M | 10.9 / 33.6 GB | Unified memory | up to 32k | — | — |
| GeForce RTX 5060 Ti 16GB | Runs greatDetails | est. 30.3 tok/s26.7–34.0calibrated estimate ±12% | Q4_K_M | 11.5 / 16.0 GB | Full GPU | up to 32k | — | $569 street (as of 2026-08-09) |
| GeForce RTX 4080 Laptop | Runs great | est. 29.2 tok/s25.7–32.7calibrated estimate ±12% | Q4_K_M | 11.5 / 12.0 GB | Full GPU | up to 8k | — | — |
| Apple M5 Max (32-core GPU) · 36 GB | Runs great | est. 26.7 tok/s21.3–32.0calibrated estimate ±20% | Q4_K_M | 10.9 / 25.2 GB | Unified memory | up to 16k | — | — |
| Intel Arc B580 | Runs great | est. 26.0 tok/s20.8–31.2calibrated estimate ±20% | Q4_K_M | 11.5 / 12.0 GB | Full GPU | up to 8k | — | $290 street (as of 2026-08-09) |
| GeForce RTX 3060 12GB | Runs greatDetails | est. 24.4 tok/s21.4–27.3calibrated estimate ±12% | Q4_K_M | 11.5 / 12.0 GB | Full GPU | up to 8k | — | $250 street (as of 2026-08-09) |
| Radeon RX 9060 XT 16GB | Runs great | est. 24.3 tok/s21.4–27.2calibrated estimate ±12% | Q4_K_M | 11.5 / 16.0 GB | Full GPU | up to 16k | — | $449 street (as of 2026-08-09) |
| Apple M4 Max (32-core GPU) · 36 GB | Runs great | est. 23.8 tok/s19.0–28.5calibrated estimate ±20% | Q4_K_M | 10.9 / 25.2 GB | Unified memory | up to 16k | — | — |
| GeForce RTX 2080 Ti | Runs well | est. 27.9 tok/s22.3–33.5calibrated estimate ±20% | Q4_K_M | 11.0 / 11.0 GB + 0.5 GB RAM | Partial offload | up to 8k |
| $999 launch MSRP |
| GeForce GTX 1080 Ti | Runs well | est. 23.8 tok/s16.7–30.9theoretical estimate ±30% | Q4_K_M | 11.0 / 11.0 GB + 0.5 GB RAM | Partial offload | up to 8k |
| $699 launch MSRP |
| GeForce RTX 4060 Ti 16GB | Runs well | est. 19.5 tok/s17.2–21.8calibrated estimate ±12% | Q4_K_M | 11.5 / 16.0 GB | Full GPU | up to 32k |
| $499 launch MSRP |
| Apple M5 Pro · 24 GB | Runs well | est. 17.8 tok/s14.2–21.4calibrated estimate ±20% | Q4_K_M | 10.9 / 16.8 GB | Unified memory | up to 32k |
| — |
| Ryzen AI Max+ 395 (Strix Halo) · 32 GB | Runs well | est. 16.1 tok/s12.9–19.3calibrated estimate ±20% | Q4_K_M | 10.9 / 22.4 GB | Unified memory | up to 32k |
| $1,999 launch MSRP |
| Apple M4 Pro · 24 GB | Runs wellDetails | est. 15.8 tok/s12.7–19.0calibrated estimate ±20% | Q4_K_M | 10.9 / 16.8 GB | Unified memory | up to 32k |
| — |
| NVIDIA DGX Spark · 128 GB | Runs well | est. 10.6 tok/s8.4–12.7calibrated estimate ±20% | Q4_K_M | 10.9 / 89.6 GB | Unified memory | up to 16k | — | $3,999 launch MSRP |
| Apple M5 · 16 GB | Runs well | est. 8.9 tok/s7.1–10.7calibrated estimate ±20% | Q4_K_M | 10.9 / 11.2 GB | Unified memory | up to 8k | — | — |
| GeForce RTX 3080 10GB | Runs slowly | est. 18.2 tok/s14.5–21.8calibrated estimate ±20% | Q4_K_M | 10.0 / 10.0 GB + 1.5 GB RAM | Partial offload | up to 32k |
| $699 launch MSRP |
| GeForce RTX 3070 | Runs slowly | est. 9.1 tok/s7.3–10.9calibrated estimate ±20% | Q4_K_M | 8.0 / 8.0 GB + 3.5 GB RAM | Partial offload | up to 32k |
| $499 launch MSRP |
| GeForce RTX 5060 | Runs slowly | est. 9.1 tok/s7.3–10.9calibrated estimate ±20% | Q4_K_M | 8.0 / 8.0 GB + 3.5 GB RAM | Partial offload | up to 32k |
| $339 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 8GB | Runs slowly | est. 9.1 tok/s7.3–10.9calibrated estimate ±20% | Q4_K_M | 8.0 / 8.0 GB + 3.5 GB RAM | Partial offload | up to 32k |
| $429 street (as of 2026-08-09) |
| GeForce RTX 4060 Ti 8GB | Runs slowly | est. 8.2 tok/s6.6–9.9calibrated estimate ±20% | Q4_K_M | 8.0 / 8.0 GB + 3.5 GB RAM | Partial offload | up to 32k |
| $399 launch MSRP |
| GeForce RTX 4060 | Runs slowlyDetails | est. 8.1 tok/s6.5–9.7calibrated estimate ±20% | Q4_K_M | 8.0 / 8.0 GB + 3.5 GB RAM | Partial offload | up to 32k |
| $299 launch MSRP |
| GeForce RTX 4060 Laptop | Runs slowly | est. 8.0 tok/s6.4–9.6calibrated estimate ±20% | Q4_K_M | 8.0 / 8.0 GB + 3.5 GB RAM | Partial offload | up to 32k |
| — |
| GeForce RTX 4070 Laptop | Runs slowly | est. 8.0 tok/s6.4–9.6calibrated estimate ±20% | Q4_K_M | 8.0 / 8.0 GB + 3.5 GB RAM | Partial offload | up to 32k |
| — |
| GeForce RTX 3050 8GB | Runs slowly | est. 7.7 tok/s6.1–9.2calibrated estimate ±20% | Q4_K_M | 8.0 / 8.0 GB + 3.5 GB RAM | Partial offload | up to 32k |
| $249 launch MSRP |
| Apple M4 · 16 GB | Runs slowlyDetails | est. 7.0 tok/s5.6–8.4calibrated estimate ±20% | Q4_K_M | 10.9 / 11.2 GB | Unified memory | up to 8k |
| — |
| DDR5-6000 dual-channel CPU · 16 GB | Runs slowly | est. 4.6 tok/s3.7–5.6calibrated estimate ±20% | Q4_K_M | 10.3 GB RAM | CPU only | up to 16k | — | — |
| DDR5-5600 dual-channel CPU · 16 GB | Runs slowly | est. 4.3 tok/s3.5–5.2calibrated estimate ±20% | Q4_K_M | 10.3 GB RAM | CPU only | up to 16k | — | — |
| DDR4-3200 dual-channel CPU · 16 GB | Runs slowly | est. 2.5 tok/s2.0–3.0calibrated estimate ±20% | Q4_K_M | 10.3 GB RAM | CPU only | up to 16k | — | — |
Cheapest GPUs that run it
- Runs greatGeForce RTX 3060 12GB$250 street (as of 2026-08-09), est. 24.4 tok/s (21.4–27.3, calibrated estimate ±12%).
Measured results for Qwen3 14B
No public measurements for this model yet.
Frequently asked questions
How much VRAM does Qwen3 14B need?
At Q4_K_M the weights are 9.00 GB; with 8k context the total is about 10.9 GB (KV cache 1.3 GB, compute buffer 0.6 GB). The smallest tracked file (Q2_K (heavy quality loss)) needs about 7.7 GB.
What is the cheapest GPU that runs Qwen3 14B well?
Cheapest that runs it great: GeForce RTX 3060 12GB at $250 (street price as of 2026-08-09), est. 24.4 tok/s (21.4–27.3, calibrated estimate ±12%).
Can Qwen3 14B run on an 8 GB, 16 GB or 24 GB GPU?
At Q4_K_M with 8k context: GeForce RTX 4060 — Runs slowly, est. 8.1 tok/s (6.5–9.7, calibrated estimate ±20%); GeForce RTX 5060 Ti 16GB — Runs great, est. 30.3 tok/s (26.7–34.0, calibrated estimate ±12%); GeForce RTX 3090 — Runs great, est. 63.4 tok/s (55.7–71.0, 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.