Yes — with 41.0 GB to spare
Qwen3 14B at Q4_K_M fits your CPU only · DDR5 dual-channel entirely on the GPU at 8K context, at an estimated 4.5 tokens per second. There is room for its full 128K window.
The largest Qwen3 that fits a 12 GB card at Q4 with room for context.
Hardware requirements What hardware do I need to run Qwen3 14B? →At Q4_K_M with an 8K context: a 16 GB GPU (RTX 5080) or a 24 GB Mac (M4 Pro). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.
The VRAM budget
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| F16 | 27.6 GB | 29.4 GB | 128K | 1.4 | Reference | Long context |
| Q8_0 | 14.6 GB | 16.5 GB | 128K | 2.6 | −0.1% ppl | Long context |
| Q6_K | 11.3 GB | 13.2 GB | 128K | 3.3 | −0.4% ppl | Long context |
| Q5_K_M | 9.8 GB | 11.6 GB | 128K | 3.9 | −0.8% ppl | Long context |
| Q4_K_M | 8.3 GB | 10.2 GB | 128K | 4.5 | −1.9% ppl | Recommended |
| Q3_K_M | 6.7 GB | 8.6 GB | 128K | 5.6 | −5.4% ppl | Long context |
| Q2_K | 5.8 GB | 7.6 GB | 128K | 6.5 | −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.
How to run it
$ llama-server \
-hf Qwen/Qwen3-14B:Q4_K_M \
-c 8192 -ngl 99
The engine underneath most of the others. Every knob is exposed. More on llama.cpp.
Related models on a CPU only · DDR5 dual-channel
| Model | Total | Tok/s est. | |
|---|---|---|---|
| Qwen3 8B 8.19B · same family |
Q4_K_M · 6.3 GB | 8.2 | Runs great |
| Qwen3 30B-A3B 30.5B MoE · same family |
Q4_K_M · 18.5 GB | 9.0 | Runs great |
| Qwen3 Coder 30B-A3B 30.5B MoE · same family |
Q4_K_M · 18.5 GB | 9.0 | Runs great |
| Qwen3 32B 32.8B · same family |
Q4_K_M · 21.0 GB | 2.0 | Runs great |
| DeepSeek-R1-Distill-Qwen 14B 14.8B · similar size |
Q4_K_M · 10.4 GB | 4.5 | Runs great |
| Qwen2.5-Coder 14B 14.8B · similar size |
Q4_K_M · 10.4 GB | 4.5 | Runs great |
| Phi-4 14B 14.7B · similar size |
Q4_K_M · 10.4 GB | 4.6 | Runs great |
Qwen3 14B on other hardware
| Device | Total | Tok/s est. | |
|---|---|---|---|
| GeForce RTX 4060 Laptop 7.0 GB usable · 256 GB/s |
10.2 GB | ~8.3 | CPU offload |
| GeForce RTX 3060 12 GB 10.6 GB usable · 360 GB/s |
10.2 GB | 26 | Tight fit |
| GeForce RTX 5080 14.4 GB usable · 960 GB/s |
10.2 GB | 70 | Runs great |
| M4 · 16 GB 10.7 GB usable · 120 GB/s |
10.2 GB | 8.1 | Tight fit |
| GeForce RTX 4090 22.4 GB usable · 1008 GB/s |
10.2 GB | 73 | Runs great |
| Radeon RX 7900 XTX 22.4 GB usable · 960 GB/s |
10.2 GB | 70 | Runs great |
| M4 Pro · 24 GB 18.0 GB usable · 273 GB/s |
10.2 GB | 18 | Runs great |
| M3 Max · 64 GB 48.0 GB usable · 400 GB/s |
10.2 GB | 27 | Runs great |