NVIDIA GeForce RTX 4090
24 GB · 1,008 GB/s · 450 W
In short
The NVIDIA GeForce RTX 4090 has 24 GB of GDDR6X memory with 1,008 GB/s of bandwidth, which sets how fast it generates text. At 128k context it runs 25 of the 113 open models we track fully in memory; the most capable is Gemma 4 26B-A4B at Q5_K_M, at about 64 tok/s (estimated). The best new price for the NVIDIA GeForce RTX 4090 in Canada is $3,300 at eBay; used, it starts at $4,450 (asking price).
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in Canada, cheapest first. Buy links may earn us a commission.
| Retailer | Condition | Price | Stock | Checked | Buy |
|---|---|---|---|---|---|
| eBayASUS ROG Strix GeForce RTX 4090 OC 24GB GDDR6X Graphics Card | New | $3,300 | In stock | 2 h ago | Buy |
| eBayNVIDIA MSI GeForce RTX 4090 GAMING TRIO X OC 24GB GDDR6X Graphics Card | used, asking price | $4,450 | In stock | 2 h ago | Buy |
| eBayASUS TUF RTX 4090 24GB | used, asking price | $4,500+ $200 delivery | In stock | 2 h ago | Buy |
| eBayGigabyte NVIDIA GeForce RTX 4090 Gaming OC 24GB Graphics Card | used, asking price | $4,990+ $450 delivery | In stock | 2 h ago | Buy |
| eBayMSI GeForce RTX 4090 Gaming Trio 24GB GDDR6X No Mining Tested | used, asking price | $6,000+ $150 delivery | In stock | 2 h ago | Buy |
| eBayASUS TUF GeForce RTX 4090 24GB OG Gaming GPU | used, asking price | $7,000 | In stock | 2 h ago | Buy |
| AmazonASUS ROG Strix GeForce RTX 4090 Gaming Graphics Card | New | $7,107+ $6 delivery | In stock | 40 min ago | Buy |
| AmazonASUS TUF GeForce RTX 4090 OC Edition Gaming Graphics Card | New | $8,527+ $6 delivery | In stock | 35 min ago | Buy |
| AmazonMSI GeForce RTX 4090 SUPRIM Liquid X 24G Gaming Graphics Card | New | $14,473 | In stock | 30 min ago | Buy |
Price history
Lowest price shown each day over the last 90 days.
Not enough price history yet.
What it runs
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Gemma 4 26B-A4B | Q5_K_M | fits | 22.1 GB | 177k256k with q8 cache | 64tok/sest. | 5385 tok/s | chat, coding, agents, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 15.7 GB | 128k | 66tok/sest. | 3487 tok/s | chat, coding, agents, long documents |
| Gemma 4 12B | Q8_0 | fits | 15.6 GB | 256k | 41tok/sest. | 2238 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 14.4 GB | 256k | 45tok/sest. | 2662 tok/s | chat, coding, long documents |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 9.7 GB | 256k | 71tok/sest. | 4146 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q4_K_M | fits | 23.3 GB | 128k233k with q8 cache | 27tok/sest. | 1366 tok/s | chat, coding, long documents |
| Gemma 4 E4B | Q8_0 | fits | 12.6 GB | 128k | 52tok/sest. | 3732 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 15.8 GB | 125k | 50tok/sest. | 4988 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q5_K_M | fits | 22.8 GB | 128k | 27tok/sest. | 1473 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 3.4 GB | 32k | 292tok/sest. | 11207 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 3.7 GB | 256k | 256tok/sest. | 14945 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 4.3 GB | 256k | 204tok/sest. | 9557 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 6.7 GB | 128k | 111tok/sest. | 5007 tok/s | chat, coding, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 15.3 GB | 128k | 82tok/sest. | 5770 tok/s | chat, coding, agents, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 9.2 GB | 128k | 75tok/sest. | 2692 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 11.6 GB | 128k | 57tok/sest. | 3453 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 11.6 GB | 32k | 57tok/sest. | 3322 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 21.8 GB | 128k | 51tok/sest. | 3623 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 14.8 GB | 128k | 44tok/sest. | 2131 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 15.1 GB | 128k | 43tok/sest. | 2173 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 15.8 GB | 128k | 41tok/sest. | 1169 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 16.0 GB | 128k | 40tok/sest. | 1788 tok/s | chat, coding, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 17.4 GB | 64k | 37tok/sest. | 1169 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q5_K_M | fits | 22.8 GB | 128k | 27tok/sest. | 1473 tok/s | chat, coding, long documents |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q4_K_M | fits | 23.3 GB | 128k233k with q8 cache | 27tok/sest. | 1366 tok/s | chat, coding, agents, long documents |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 24.9 GB | 105k184k with q8 cache | 15tok/sest. | 877 tok/s | chat, coding, agents |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 43.6 GB | – | 9tok/sest. | 1156 tok/s | chat |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 25.3 GB | 100k176k with q8 cache | 13tok/sest. | 870 tok/s | chat, coding, agents |
| Gemma 4 31B | Q4_K_M | offload | 29.3 GB | 57k110k with q8 cache | 6tok/sest. | 756 tok/s | chat, coding |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 41.7 GB | – | 12tok/sest. | 1023 tok/s | chat, coding |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 24.2 GB | 95k149k with q8 cache | 59tok/sest. | 4340 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 25.2 GB | 101k178k with q8 cache | 14tok/sest. | 872 tok/s | chat, coding, agents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 24.5 GB | 84k131k with q8 cache | 54tok/sest. | 4308 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 25.1 GB | 98k169k with q8 cache | 21tok/sest. | 2002 tok/s | chat, coding, agents, long documents |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 34.8 GB | 57k105k with q8 cache | 4tok/sest. | 649 tok/s | chat, coding, agents |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 34.8 GB | – | 19tok/sest. | 4740 tok/s | chat, coding, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 30.5 GB | – | 36tok/sest. | 2842 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 30.7 GB | 54k97k with q8 cache | 7tok/sest. | 1097 tok/s | chat, coding, agents |
| Gemma 3 27B | Q4_K_M | offload | 27.3 GB | 81k128k with q8 cache | 9tok/sest. | 1017 tok/s | chat, coding |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 34.8 GB | 57k105k with q8 cache | 4tok/sest. | 649 tok/s | chat, coding |
| Ministral 3 14B Mistral AI | Q4_K_M | offload | 29.1 GB | 92k169k with q8 cache | 7tok/sest. | 918 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q4_K_M | offload | 29.8 GB | 40k | 6tok/sest. | 771 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q4_K_M | offload | 24.1 GB | 122k128k with q8 cache | 19tok/sest. | 1323 tok/s | chat, coding, long documents |
| Qwen3 8B Alibaba Qwen | Q4_K_M | offload | 24.1 GB | 40k | 19tok/sest. | 1323 tok/s | chat, coding, long documents |
| Phi-4 14B Microsoft | Q4_K_M | offload | 34.7 GB | 16k | 4tok/sest. | 712 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q4_K_M | offload | 26.6 GB | 108k128k with q8 cache | 10tok/sest. | 1133 tok/s | chat, coding, agents |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | offload | 25.7 GB | 100k128k with q8 cache | 15tok/sest. | 2746 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | offload | 33.8 GB | 74k128k with q8 cache | 4tok/sest. | 638 tok/s | chat, coding |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 34.8 GB | 57k105k with q8 cache | 4tok/sest. | 655 tok/s | chat, coding, agents |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 34.8 GB | 40k | 4tok/sest. | 655 tok/s | chat, coding |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 34.8 GB | 40k | 4tok/sest. | 655 tok/s | chat, coding, agents |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 34.8 GB | 57k105k with q8 cache | 4tok/sest. | 649 tok/s | chat, coding, agents |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 102.4 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 104.2 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 78.0 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 102.6 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 53.5 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 49.7 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 64.4 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 66.7 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 49.7 GB | – | – | – | – |
| Qwen3 32B Alibaba Qwen | Q4_K_M | won't run | 51.9 GB | 16k30k with q8 cache | – | – | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | won't run | 51.9 GB | 16k30k with q8 cache | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 81.1 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 386.7 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 387.2 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 81.1 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 386.7 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 387.6 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 387.6 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 157.8 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 166.6 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | won't run | 169.2 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 83.7 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 90.1 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 249.0 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 432.4 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 446.3 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 758.7 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 588.2 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 588.6 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 588.6 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 588.6 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 161.3 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 161.3 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 147.7 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 263.2 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 115.2 GB | – | – | – | – |
| granite 4.2 30b IBM | Q4_K_M | won't run | 50.2 GB | 23k42k with q8 cache | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- GeForce RTX 4090
- Memory
- 24 GB GDDR6X
- Memory bus
- 384-bit
- Memory bandwidth
- 1,008 GB/s
- FP16 compute
- 165 TFLOPS
- Software
- CUDA
- Board power
- 450 W
- PCIe generation
- Gen 4
- PCIe lanes
- x16
Compare with
Questions
- How much memory does the NVIDIA GeForce RTX 4090 have for AI models?
- The NVIDIA GeForce RTX 4090 has 24 GB of GDDR6X memory with 1,008 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the NVIDIA GeForce RTX 4090 can run locally?
- Gemma 4 26B-A4B (Q5_K_M) fits fully in its memory at 128k context and generates at about 64 tok/s, an estimate from its memory bandwidth. 25 of the 113 models we track fit at that context.
- Can the NVIDIA GeForce RTX 4090 run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 102 GB at 128k context, more than the NVIDIA GeForce RTX 4090 and system RAM can hold.
- How much does the NVIDIA GeForce RTX 4090 cost in Canada?
- The best new price for the NVIDIA GeForce RTX 4090 in Canada is $3,300 at eBay; used, it starts at $4,450 (asking price).
Speeds on this page are for 128k context. See the best hardware for local AI at every budget.