NVIDIA GeForce RTX 4060
8 GB · 272 GB/s · 115 W
In short
The NVIDIA GeForce RTX 4060 has 8 GB of GDDR6 memory with 272 GB/s of bandwidth, which sets how fast it generates text. At 64k context it runs 27 of the 129 open models we track fully in memory; the most capable is gpt-oss 20B at MXFP4, at about 25 tok/s (estimated). The NVIDIA GeForce RTX 4060 is not on sale new in the US right now; used, it starts at $415 (asking price).
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in the US, cheapest first. Buy links may earn us a commission.
| Retailer | Condition | Price | Stock | Checked | Buy |
|---|---|---|---|---|---|
| eBayUsed GeForce RTX 4060 on eBay | used, asking price | $415 | In stock | 6 h ago | Buy |
Used on eBay: median asking price $415, most between $400 and $456 (40 listings, 2026-11-03). Used price history
Price history
Lowest price shown each day over the last 90 days.
Not enough price history yet.
What two of them run
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.3 GB | 82k128k with q8 cache | 25tok/sest. | 458 tok/s | chat, coding, agents |
| Gemma 4 12B | Q8_0 | fits | 14.6 GB | 73k122k with q8 cache | 12tok/sest. | 236 tok/s | – |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.4 GB | 128k212k with q8 cache | 14tok/sest. | 288 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.7 GB | 255k256k with q8 cache | 25tok/sest. | 500 tok/s | chat, coding, long documents |
| Gemma 4 E4B | Q8_0 | fits | 10.9 GB | 128k | 17tok/sest. | 378 tok/s | chat |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 12.9 GB | 100k125k with q8 cache | 24tok/sest. | 806 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q4_K_M | fits | 14.1 GB | 69k126k with q8 cache | 13tok/sest. | 205 tok/s | chat |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.7 GB | 32k | 126tok/sest. | 1787 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 3.0 GB | 256k | 103tok/sest. | 2026 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.6 GB | 256k | 75tok/sest. | 1104 tok/s | chat, coding, agents, long documents |
| LFM3 1.7B Liquid AI | Q8_0 | fits | 4.0 GB | 256k | 63tok/sest. | 1332 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 5.0 GB | 128k | 45tok/sest. | 740 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 6.6 GB | 128k | 31tok/sest. | 417 tok/s | chat, coding, agents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 6.6 GB | 263k441k with q8 cache | 31tok/sest. | 512 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 14.4 GB | 83k125k with q8 cache | 28tok/sest. | 747 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q4_K_M | fits | 13.2 GB | 109k128k with q8 cache | 26tok/sest. | 513 tok/s | chat, coding, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 7.8 GB | 251k256k with q8 cache | 25tok/sest. | 500 tok/s | chat, coding, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 7.9 GB | 128k | 24tok/sest. | 506 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 7.9 GB | 32k | 24tok/sest. | 476 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-5bit | fits | 14.4 GB | 75k123k with q8 cache | 24tok/sest. | 403 tok/s | chat, coding, agents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 9.8 GB | 122k128k with q8 cache | 19tok/sest. | 318 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 10.1 GB | 119k128k with q8 cache | 18tok/sest. | 328 tok/s | chat, coding |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 11.4 GB | 95k172k with q8 cache | 16tok/sest. | 314 tok/s | chat, coding |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 11.7 GB | 32k | 15tok/sest. | 169 tok/s | chat |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 12.5 GB | 101k128k with q8 cache | 14tok/sest. | 240 tok/s | chat |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 13.3 GB | 97k128k with q8 cache | 13tok/sest. | 162 tok/s | chat |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q4_K_M | fits | 14.1 GB | 69k126k with q8 cache | 13tok/sest. | 205 tok/s | chat |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 20.9 GB | – | 5tok/sest. | 81 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 21.3 GB | – | 5tok/sest. | 80 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 24.3 GB | – | 4tok/sest. | 68 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 40.3 GB | – | 11tok/sest. | 123 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 23.0 GB | – | 17tok/sest. | 462 tok/s | chat, coding |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 21.2 GB | – | 5tok/sest. | 80 tok/s | – |
| Gemma 4 26B-A4B | MXFP4 | offload | 18.3 GB | – | 17tok/sest. | 536 tok/s | chat, coding |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 23.3 GB | – | 17tok/sest. | 459 tok/s | chat, coding |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 21.8 GB | – | 9tok/sest. | 235 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 24.8 GB | 2k3k with q8 cache | 4tok/sest. | 73 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | MXFP4 | offload | 23.5 GB | – | 21tok/sest. | 563 tok/s | chat, coding, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 30.0 GB | – | 20tok/sest. | 327 tok/s | chat, coding |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 24.8 GB | – | 6tok/sest. | 159 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 35.9 GB | – | 2tok/sest. | 32 tok/s | – |
| Gemma 3 27B | Q4_K_M | offload | 22.3 GB | – | 4tok/sest. | 87 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 24.8 GB | 2k3k with q8 cache | 4tok/sest. | 73 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 36.0 GB | – | 2tok/sest. | 40 tok/s | – |
| Ministral 3 14B Mistral AI | Q4_K_M | offload | 19.1 GB | 37k67k with q8 cache | 6tok/sest. | 117 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q4_K_M | offload | 19.9 GB | 32k40k with q8 cache | 5tok/sest. | 101 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q4_K_M | offload | 15.2 GB | 61k111k with q8 cache | 11tok/sest. | 188 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q4_K_M | offload | 15.2 GB | 40k | 11tok/sest. | 188 tok/s | chat |
| Phi-4 14B Microsoft | Q4_K_M | offload | 22.3 GB | 16k | 4tok/sest. | 95 tok/s | chat |
| Ministral 3 8B Mistral AI | Q4_K_M | offload | 14.8 GB | 63k115k with q8 cache | 12tok/sest. | 188 tok/s | chat |
| Granite 4.2 8B IBM | Q4_K_M | offload | 16.6 GB | 52k96k with q8 cache | 8tok/sest. | 162 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q4_K_M | offload | 14.8 GB | 63k115k with q8 cache | 12tok/sest. | 188 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | offload | 14.9 GB | 60k64k with q8 cache | 11tok/sest. | 161 tok/s | – |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | offload | 20.8 GB | – | 9tok/sest. | 376 tok/s | chat |
| Muse Glimmer 30B meta-models | Q4_K_M | offload | 18.5 GB | – | 6tok/sest. | 87 tok/s | – |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q4_K_M | offload | 19.1 GB | 37k67k with q8 cache | 6tok/sest. | 117 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | offload | 21.8 GB | 27k50k with q8 cache | 4tok/sest. | 87 tok/s | chat |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 24.8 GB | 2k3k with q8 cache | 4tok/sest. | 74 tok/s | – |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 24.8 GB | 2k3k with q8 cache | 4tok/sest. | 74 tok/s | – |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 24.8 GB | 2k3k with q8 cache | 4tok/sest. | 74 tok/s | – |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 24.8 GB | 2k3k with q8 cache | 4tok/sest. | 73 tok/s | – |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | offload | 24.9 GB | – | 4tok/sest. | 74 tok/s | – |
| granite 4.2 30b IBM | Q4_K_M | offload | 34.3 GB | – | 2tok/sest. | 47 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 97.0 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.5 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 76.5 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 87.1 GB | – | – | – | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | won't run | 42.1 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 53.0 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 48.2 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 62.2 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 55.2 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 48.2 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 61.1 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 382.9 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 61.1 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 382.4 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 383.3 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 383.3 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 383.3 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 152.5 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 161.3 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 93.2 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 226.1 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 72.2 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 225.3 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 78.6 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 226.1 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 389.3 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 426.9 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 440.8 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 753.3 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 81.4 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 583.9 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 584.3 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 584.3 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 584.3 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 145.8 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 145.8 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 132.2 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 248.7 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 93.2 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- GeForce RTX 4060
- Memory
- 8 GB GDDR6
- Memory bus
- 128-bit
- Memory bandwidth
- 272 GB/s
- FP16 compute
- 15.114 TFLOPS
- Software
- CUDA
- Board power
- 115 W
- PCIe generation
- Gen 4
- PCIe lanes
- x8
Compare with
Questions
- How much memory does the NVIDIA GeForce RTX 4060 have for AI models?
- The NVIDIA GeForce RTX 4060 has 8 GB of GDDR6 memory with 272 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the NVIDIA GeForce RTX 4060 can run locally?
- gpt-oss 20B (MXFP4) fits fully in its memory at 64k context and generates at about 25 tok/s, an estimate from its memory bandwidth. 27 of the 129 models we track fit at that context.
- Can the NVIDIA GeForce RTX 4060 run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 97 GB at 64k context, more than the NVIDIA GeForce RTX 4060 and system RAM can hold.
- How much does the NVIDIA GeForce RTX 4060 cost in the US?
- The NVIDIA GeForce RTX 4060 is not on sale new in the US right now; used, it starts at $415 (asking price).
Speeds on this page are for 64k context. See the best hardware for local AI at every budget.