Used RTX 3090 workhorse
$3,482
Parts
Compatibility: No problems found.Est. load 490 W of 850 W · spikes to 700 W
| Component | Selection | Price | Where | Buy |
|---|---|---|---|---|
| GPU | NVIDIA GeForce RTX 3090 24 GB · 936 GB/s · 350 W | $1,600 | eBay | Buy |
| CPU | AMD Ryzen 7 7700 AM5 · 8 cores · 24 PCIe lanes | $139 | eBay (used) | Buy |
| Motherboard | MSI MAG B650 Tomahawk WiFi AM5 · DDR5 · ATX | $140 | eBay | Buy |
| Memory | G.Skill Flare X5 64GB (2×32GB) DDR5-6000 64 GB · DDR5-6000 | $1,133 | eBay | Buy |
| Power supply | Corsair RM850x ATX 3.1 850W 850 W · ATX 3 | $90 | eBay | Buy |
| Case | Fractal Design North GPUs up to 355 mm | $80 | eBay | Buy |
| Storage | Samsung 990 Pro 2TB 2000 GB NVME | $300 | eBay | Buy |
| Total | $3,482 | |||
- Note: Check the power connectors on the card you buy: this power supply has 1 12V-2x6 and 3 8-pin PCIe connectors.
- Note: Fractal Design North fits graphics cards up to 355 mm: check the length of the card you buy.
What this build runs
The most precise quant that fits, at 8k context. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | UD-Q6_K | fits | 21.9 GB | 30k53k with q8 cache | 26tok/sest. | 559 tok/s | chat, coding |
| Qwen 3.6 27B Alibaba Qwen | Q6_K | fits | 22.4 GB | 23k40k with q8 cache | 25tok/sest. | 559 tok/s | chat |
| Gemma 4 31B | Q5_K_M | fits | 22.3 GB | 20k44k with q8 cache | 25tok/sest. | 487 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q4_K_M | fits | 21.7 GB | 74k116k with q8 cache | 167tok/sest. | 4789 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q6_K | fits | 22.3 GB | 24k42k with q8 cache | 25tok/sest. | 559 tok/s | chat |
| Gemma 4 26B-A4B | UD-Q6_K | fits | 22.7 GB | 36k62k with q8 cache | 88tok/sest. | 3649 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | fits | 21.5 GB | 84k131k with q8 cache | 168tok/sest. | 4789 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q5_K_M | fits | 21.1 GB | 48k82k with q8 cache | 87tok/sest. | 2680 tok/s | chat, coding, agents |
| Devstral Small 2 24B Mistral AI | Q6_K | fits | 20.0 GB | 28k52k with q8 cache | 28tok/sest. | 630 tok/s | chat |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.2 GB | 128k | 132tok/sest. | 3466 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q5_K_M | fits | 21.7 GB | 24k44k with q8 cache | 118tok/sest. | 3465 tok/s | chat, coding, agents |
| Qwen3 32B Alibaba Qwen | Q4_K_M | fits | 21.2 GB | 16k30k with q8 cache | 27tok/sest. | 431 tok/s | chat |
| Gemma 4 12B | Q8_0 | fits | 13.0 GB | 256k | 44tok/sest. | 1272 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 9.9 GB | 256k | 59tok/sest. | 1610 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q6_K | fits | 20.0 GB | 28k52k with q8 cache | 28tok/sest. | 630 tok/s | chat |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | fits | 21.2 GB | 16k30k with q8 cache | 26tok/sest. | 451 tok/s | chat |
| Gemma 3 27B | Q6_K | fits | 22.4 GB | 19k38k with q8 cache | 25tok/sest. | 566 tok/s | chat |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.4 GB | 57k104k with q8 cache | 37tok/sest. | 1045 tok/s | chat, coding |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 16.6 GB | 40k | 34tok/sest. | 971 tok/s | chat, coding |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.0 GB | 99k128k with q8 cache | 59tok/sest. | 1700 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.0 GB | 40k | 59tok/sest. | 1700 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 16.8 GB | 16k | 34tok/sest. | 978 tok/s | chat, coding |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.2 GB | 256k | 121tok/sest. | 3242 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.2 GB | 103k187k with q8 cache | 57tok/sest. | 1588 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 10.7 GB | 86k128k with q8 cache | 54tok/sest. | 1576 tok/s | chat, coding, agents |
| Gemma 4 E4B | Q8_0 | fits | 8.6 GB | 128k | 69tok/sest. | 1951 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.5 GB | 125k | 237tok/sest. | 11389 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 7.9 GB | 126k128k with q8 cache | 76tok/sest. | 1755 tok/s | chat, coding, long documents |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.3 GB | 32k | 919tok/sest. | 23836 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 1.6 GB | 256k | 623tok/sest. | 16400 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.2 GB | 256k | 373tok/sest. | 6727 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 2.7 GB | 128k | 273tok/sest. | 7502 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 3.6 GB | 128k | 191tok/sest. | 4959 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 3.9 GB | 128k | 172tok/sest. | 4991 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 3.9 GB | 32k | 172tok/sest. | 4405 tok/s | chat, coding, agents, long documents |
| LFM2.5 24B A2B Liquid AI | Q6_K | fits | 21.1 GB | 35k63k with q8 cache | 143tok/sest. | 5981 tok/s | chat, coding, agents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 4.7 GB | 128k | 135tok/sest. | 3303 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 5.0 GB | 128k | 127tok/sest. | 3551 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 12.9 GB | 128k | 123tok/sest. | 5488 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 17.6 GB | 128k | 99tok/sest. | 4626 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 8.7 GB | 128k | 68tok/sest. | 1893 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 9.7 GB | 112k128k with q8 cache | 60tok/sest. | 1755 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 10.2 GB | 103k187k with q8 cache | 57tok/sest. | 1588 tok/s | chat, coding, agents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 10.4 GB | 128k | 56tok/sest. | 1373 tok/s | chat, coding, agents, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 12.0 GB | 64k | 48tok/sest. | 1373 tok/s | chat, coding, long documents |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 16.9 GB | 41k76k with q8 cache | 34tok/sest. | 952 tok/s | chat, coding |
| Devstral Small 2507 Mistral AI | Q5_K_M | fits | 17.6 GB | 43k79k with q8 cache | 32tok/sest. | 641 tok/s | chat, coding |
| Magistral Small 2507 Mistral AI | Q5_K_M | fits | 17.6 GB | 40k | 32tok/sest. | 641 tok/s | chat, coding |
| Magistral Small 2509 Mistral AI | Q5_K_M | fits | 17.6 GB | 43k79k with q8 cache | 32tok/sest. | 630 tok/s | chat, coding |
| Magistral Small 2506 Mistral AI | Q6_K | fits | 20.0 GB | 28k40k with q8 cache | 28tok/sest. | 641 tok/s | chat |
| granite 4.2 30b IBM | Q5_K_M | fits | 22.3 GB | 12k22k with q8 cache | 25tok/sest. | 508 tok/s | chat |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | offload | 74.5 GB | – | 2tok/sest. | 150 tok/s | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | offload | 72.8 GB | – | 8tok/sest. | 665 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.0 GB | – | 19tok/sest. | 1103 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 46.2 GB | – | 24tok/sest. | 2611 tok/s | chat |
| gpt-oss 120B OpenAI | Q4_K_M | offload | 59.5 GB | – | 16tok/sest. | 1583 tok/s | chat |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 51.9 GB | – | 10tok/sest. | 867 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 38.4 GB | – | 29tok/sest. | 1471 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q2_K | offload | 44.4 GB | – | 8tok/sest. | 524 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 46.2 GB | – | 30tok/sest. | 3283 tok/s | chat, coding |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | offload | 33.4 GB | – | 27tok/sest. | 4071 tok/s | chat, coding, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 28.8 GB | – | 65tok/sest. | 4023 tok/s | chat, coding, long documents |
| Llama 3.3 70B Meta | Q4_K_M | offload | 42.8 GB | – | 3tok/sest. | 152 tok/s | – |
| GLM 4.5V Z.ai | Q4_K_M | offload | 61.4 GB | – | 5tok/sest. | 527 tok/s | – |
| GLM 4.6V Z.ai | Q4_K_M | offload | 67.8 GB | – | 5tok/sest. | 509 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | offload | 42.8 GB | – | 3tok/sest. | 152 tok/s | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | offload | 73.3 GB | – | 1tok/sest. | 69 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 91.6 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.2 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 378.4 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 377.9 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 147.1 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 155.8 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q8_0 | won't run | 127.2 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 205.2 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 421.4 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 435.3 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 747.8 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 579.4 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 579.9 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 131.5 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 131.5 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 118.0 GB | – | – | – | – |
| MiniMax M3 MiniMax | UD-Q4_K_M | won't run | 248.4 GB | – | – | – | – |