PC with RTX 4060 Ti 16GB (16 GB) and 32 GB RAM. Updated 2 November 2026.
PC with RTX 4060 Ti 16GB (16 GB) and 32 GB RAM can run 16 of the 31 models tracked here at a comfortable speed, and another 9 slowly. The largest chat or coding model that fits is gpt-oss 20B, which needs about 15.2 GB and generates roughly 29 words a second. The quickest is Gemma 4 E2B at about 65 words a second, which feels faster than you can read.
Video memory (VRAM) is the limit: 16 GB on this card. A model must fit in VRAM to run fast. Anything larger spills into system RAM (32 GB in this setup), which works but is slow, because system RAM moves data at roughly 70 GB/s while the card moves 288 GB/s.
Best chat pick: gpt-oss 20B at about 29 words a second. Best coding pick: Qwen2.5 Coder 7B at about 28.
Spare memory after loading the model decides how long a conversation or document can be before things slow down. With about 34 GB usable here:
The biggest single jump is Ryzen AI Max+ 395 (Strix Halo), 128 GB, which would unlock 11 more models, including Gemma 4 26B A4B, Qwen 3.5 35B A3B, Qwen 3.5 122B A10B.
For chat, gpt-oss 20B is the best fit, at about 29 words a second. For coding, Qwen2.5 Coder 7B.
Gemma 4 12B runs at about 17 words a second (runs great); gpt-oss 20B runs at about 29 words a second (runs great); Qwen 3.5 35B A3B runs at about 17 words a second (slow).
No. Llama 3.3 70B needs about 45.6 GB and this machine tops out near 34 GB.
| Model | Verdict | Speed | Needs |
|---|---|---|---|
| gpt-oss 20B | Runs great | 29 words/s | 15.2 GB |
| Phi-4 14B | Runs great | 14 words/s | 10.1 GB |
| Gemma 4 12B | Runs great | 17 words/s | 8.9 GB |
| Gemma 4 E4B | Runs great | 41 words/s | 7.4 GB |
| Qwen 3.5 9B | Runs great | 20 words/s | 7.4 GB |
| Qwen3 VL 8B | Runs great | 21 words/s | 6.9 GB |
| DeepSeek R1 8B | Runs great | 25 words/s | 6 GB |
| Qwen2.5 Coder 7B | Runs great | 28 words/s | 5.4 GB |
| Gemma 4 E2B | Runs great | 65 words/s | 5.3 GB |
| Qwen 3.5 4B | Runs great | 39 words/s | 4 GB |
| ACE-Step 1.5 | Runs well | about 3 min | 12 GB |
| FLUX.2 klein 4B | Runs well | about 34 s | 10 GB |
| Stable Diffusion XL | Runs well | about 18 s | 8 GB |
| Qwen3 TTS 1.7B | Runs well | about 52 s | 8 GB |
| Whisper large-v3 turbo | Runs well | about 1 min | 4 GB |
| Kokoro TTS | Runs well | about 11 s | 2 GB |
| Qwen 3.6 35B A3B | Slow | 16 words/s | 24.6 GB |
| Qwen 3.5 35B A3B | Slow | 17 words/s | 23.6 GB |
| Gemma 4 31B | Slow | 3 words/s | 21.5 GB |
| DeepSeek R1 32B | Slow | 3 words/s | 21.5 GB |
| Qwen3 Coder 30B | Slow | 19 words/s | 20.4 GB |
| Qwen 3.6 27B | Slow | 4 words/s | 19.9 GB |
| Gemma 4 26B A4B | Slow | 16 words/s | 19.4 GB |
| Z-Image Turbo 6B | Slow | about 2 min | 16 GB |
| Wan 2.2 5B | Slow | about 27 min | 16 GB |
As an Amazon Associate I earn from qualifying purchases.
Unlocks 7 more: Gemma 4 26B A4B, Gemma 4 31B, Qwen3 Coder 30B, Qwen 3.6 27B and more.
Unlocks 10 more: Gemma 4 26B A4B, Qwen 3.5 35B A3B, Gemma 4 31B, Qwen3 Coder 30B and more.
Unlocks 11 more: Gemma 4 26B A4B, Qwen 3.5 35B A3B, Qwen 3.5 122B A10B, gpt-oss 120B and more.