NVIDIA GEFORCE RTX 5080 (16GB)

BUY NOW AT NVIDIA →

product: NVIDIA GeForce RTX 5080 (16GB)
category: GPUs
brand: NVIDIA
memory: 16GB VRAM · 960 GB/s [2]
notes: Official starting MSRP. Partner cards may cost more.
price:
  now: $999 (NVIDIA, official msrp, 2026-11-13) [1] BUY NOW AT NVIDIA →
  since_first: FLAT SINCE JAN 30, 2025
  first_record: 2025-01-30 (price in the paid export)
  change:
    1d: —
    7d: =0.0%
    14d: —
    30d: =0.0%
    90d: =0.0%
    180d: =0.0%
  availability: in stock

FLAT SINCE JAN 30, 2025 — now $999. BUY NOW AT NVIDIA →

PRICE TREND (shape since first record)

              │                                                            
              │                                                            
              │                                                            
              │                                                            
     now $999 │████████████████████████████████████████████████████████████
              │████████████████████████████████████████████████████████████
              │████████████████████████████████████████████████████████████
              │████████████████████████████████████████████████████████████
              └────────────────────────────────────────────────────────────
               2025-01-30                                        2026-11-13
               █ recorded price  ░ gap between records · shape only; past prices are in the paid export

PRICE HISTORY (last 7 days)

2026-11-13$999NVIDIAin stock[1]
2026-11-08$999NVIDIAin stock[3]
2026-11-06$999NVIDIAin stock[4]

22 older records back to Jan 30, 2025 (every price, date and source) are in the paid export (YAML / CSV).

PAIRS WELL WITH (add-ons, not price-tracked · all peripherals)
CyberPower CP1500PFCLCD PFC sine-wave UPS:
  why: Pure sine wave output, which suits high-power GPU desktops with active-PFC power supplies.
  buy: BUY ON AMAZON →
Cable Matters DisplayPort 2.1 (DP80) cable:
  why: Full-bandwidth DisplayPort for RTX 50-series and RX 9070 cards.
  buy: BUY ON AMAZON →
WD_BLACK SN850X 2TB NVMe SSD (WDS200T2X0E):
  why: Fast PCIe 4.0 drive for a GPU desktop's model library.
  buy: BUY ON AMAZON →

CAN RUN — LOCAL MODELS THAT FIT

memory: 16GB VRAM · usable for models ≈ 15 GB (rule)
bandwidth: 960 GB/s [2]
largest_fit: gpt-oss 20B MXFP4
fits: 4 of 33 model files (excluding the Llama 2 7B reference)
note: fit = weights + KV cache at 8,192 tokens + 10% runtime overhead
Nemotron 3.5 Super 120B-A12B (MoE)Q8_0128.5 GB141.4 GB [5]nono published run
Nemotron 3.5 Super 120B-A12B (MoE)Q4_072.1 GB79.4 GB [5]nono published run
gpt-oss 120B (MoE)MXFP463.4 GB70.0 GB [6]nono published run
Llama 4 Scout 109B-A17B (MoE)Q8_0114.5 GB127.6 GB [7]nono published run
Llama 4 Scout 109B-A17B (MoE)Q4_K_M65.4 GB73.5 GB [7]nono published run
Nemotron 3.5 Bolt 74B-A9B (MoE)BF16148.2 GB163.1 GB [8]nono published run
Nemotron 3.5 Bolt 74B-A9B (MoE)Q8_078.9 GB86.8 GB [8]nono published run
Nemotron 3.5 Bolt 74B-A9B (MoE)Q4_K_XL50.2 GB55.3 GB [8]nono published run
Llama 3.3 70Bf16141.1 GB157.9 GB [9]nono published run
Llama 3.3 70BQ8_075.0 GB85.2 GB [9]nono published run
Llama 3.3 70BQ4_K_M42.5 GB49.5 GB [9]nono published run
OLMo 3.1 32Bbf1664.5 GB72.3 GB [10]nono published run
OLMo 3.1 32BQ8_034.3 GB39.0 GB [10]nono published run
OLMo 3.1 32BQ4_K_M19.5 GB22.8 GB [10]nono published run
Nemotron 3.5 Lightning 30B-A3B (MoE)BF1663.2 GB69.5 GB [11]nono published run
Nemotron 3.5 Lightning 30B-A3B (MoE)Q8_033.6 GB37.0 GB [11]nono published run
Nemotron 3.5 Lightning 30B-A3B (MoE)Q4_018.9 GB20.8 GB [11]nono published run
Gemma 4 31BBF1661.4 GB69.1 GB [12]nono published run
Gemma 4 31BQ8_032.6 GB37.4 GB [12]nono published run
Gemma 4 31BQ4_K_M18.3 GB21.7 GB [12]nono published run
Granite 4.2 30Bbf1658.6 GB66.6 GB [13]nono published run
Granite 4.2 30BQ8_031.1 GB36.4 GB [13]nono published run
Granite 4.2 30BQ4_K_M17.7 GB21.6 GB [13]nono published run
Gemma 4 26B-A4B (MoE)BF1650.5 GB55.9 GB [14]nono published run
Gemma 4 26B-A4B (MoE)Q8_026.9 GB29.9 GB [14]nono published run
Gemma 4 26B-A4B (MoE)Q4_K_M16.9 GB19.0 GB [14]nono published run
gpt-oss 20BMXFP412.1 GB13.5 GB [15]YESno published run
Phi-4 14BF1629.3 GB33.9 GB [16]nono published run
Phi-4 14BQ8_015.6 GB18.8 GB [16]nono published run
Phi-4 14BQ4_K_M8.9 GB11.5 GB [16]YESno published run
Gemma 4 12BBF1623.8 GB26.7 GB [17]nono published run
Gemma 4 12BQ8_012.7 GB14.4 GB [17]YESno published run
Gemma 4 12BQ4_K_M7.1 GB8.3 GB [17]YESno published run
Llama 2 7B (llama.cpp reference benchmark model)Q8_07.2 GB12.2 GB [18]YESno published run
Llama 2 7B (llama.cpp reference benchmark model)Q4_03.8 GB8.5 GB [18]YES182.0 tok/s tg128 [19]

WHERE TO BUY

official: BUY NOW → NVIDIA
retailers: not tracked yet (partner programs pending)
TRACK PRICES — WEEKLY EMAIL COMING SOON
Get one email a week with the price changes for the products you pick. Not live yet: this form sends nothing and stores nothing.




SOURCES

Current sources only. Every older price point and its source is in the paid export.

#whatsourcefetched
[1]RTX 5080 $999 on 2026-11-13 — Official product page JSON-LD Offer price 999 USD, availability InStock.www.nvidia.com/en-us/geforce/graphics-cards/50-series/rtx-5080/2026-11-13
[2]NVIDIA compare page: 960 GB/secwww.nvidia.com/en-us/geforce/graphics-cards/compare/2026-11-13
[3]RTX 5080 $999 on 2026-11-08web.archive.org/web/20261108014904/www.nvidia.com/en-us/geforce/gra...2026-11-13
[4]RTX 5080 $999 on 2026-11-06web.archive.org/web/20261106211642/www.nvidia.com/en-us/geforce/gra...2026-11-13
[5]Nemotron 3.5 Super 120B-A12B (MoE): GGUF sizes + config.json (KV cache at 8k)huggingface.co/ggml-org/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-GGUF2026-11-13
[6]gpt-oss 120B (MoE): GGUF sizes + config.json (KV cache at 8k)huggingface.co/ggml-org/gpt-oss-120b-GGUF2026-11-13
[7]Llama 4 Scout 109B-A17B (MoE): GGUF sizes + config.json (KV cache at 8k)huggingface.co/unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF2026-11-13
[8]Nemotron 3.5 Bolt 74B-A9B (MoE): GGUF sizes + config.json (KV cache at 8k)huggingface.co/unsloth/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-GGUF2026-11-13
[9]Llama 3.3 70B: GGUF sizes + config.json (KV cache at 8k)huggingface.co/bartowski/Llama-3.3-70B-Instruct-GGUF2026-11-13
[10]OLMo 3.1 32B: GGUF sizes + config.json (KV cache at 8k)huggingface.co/bartowski/allenai_Olmo-3.1-32B-Instruct-GGUF2026-11-13
[11]Nemotron 3.5 Lightning 30B-A3B (MoE): GGUF sizes + config.json (KV cache at 8k)huggingface.co/ggml-org/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF2026-11-13
[12]Gemma 4 31B: GGUF sizes + config.json (KV cache at 8k)huggingface.co/unsloth/gemma-4-31B-it-GGUF2026-11-13
[13]Granite 4.2 30B: GGUF sizes + config.json (KV cache at 8k)huggingface.co/ibm-granite/granite-4.2-30b-GGUF2026-11-13
[14]Gemma 4 26B-A4B (MoE): GGUF sizes + config.json (KV cache at 8k)huggingface.co/unsloth/gemma-4-26B-A4B-it-GGUF2026-11-13
[15]gpt-oss 20B: GGUF sizes + config.json (KV cache at 8k)huggingface.co/ggml-org/gpt-oss-20b-GGUF2026-11-13
[16]Phi-4 14B: GGUF sizes + config.json (KV cache at 8k)huggingface.co/unsloth/phi-4-GGUF2026-11-13
[17]Gemma 4 12B: GGUF sizes + config.json (KV cache at 8k)huggingface.co/unsloth/gemma-4-12b-it-GGUF2026-11-13
[18]Llama 2 7B (llama.cpp reference benchmark model): GGUF sizes + config.json (KV cache at 8k)huggingface.co/TheBloke/Llama-2-7B-GGUF2026-11-13
[19]CUDA scoreboard, no FAgithub.com/ggml-org/llama.cpp/discussions/150132026-11-13