home.social

#gddr7 — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #gddr7, aggregated by home.social.

fetched live
  1. Micron Ends 2GB GDDR7 Production, Leaving NVIDIA RTX 50 Supply to Samsung and SK Hynix — BigGo Finance

    Micron Technology (MU) has quietly pulled the plug on its 2GB GDDR7 memory chips, a move that removes…
    #EuropeSays #Korea #KR #SKHynix #GDDR7 #GeForceRTX50 #MicronTechnology #NVIDIA #RTXPROBlackwell #SamsungElectronics #SK #SKhynix #UNIKO'sHardware
    europesays.com/korea/166423/

  2. Az AMD már készíti a nyílt AMDGPU drivert GDDR7-hez, ami RDNA5-re utal. Új patchek (GDDR7, IH8.0, NBIF7.10) erősítik az előkészületeket — mit jelent ez neked Linuxon? Te szerinted időben kész lesz a kernel?

    linuxmint.hu/hir/2026/09/amd-e

    #AMD #RDNA5 #GDDR7 #AMDGPU #Linux #kernel #driver #NBIF

  3. Az AMD már készíti a nyílt AMDGPU drivert GDDR7-hez, ami RDNA5-re utal. Új patchek (GDDR7, IH8.0, NBIF7.10) erősítik az előkészületeket — mit jelent ez neked Linuxon? Te szerinted időben kész lesz a kernel?

    linuxmint.hu/hir/2026/09/amd-e

    #AMD #RDNA5 #GDDR7 #AMDGPU #Linux #kernel #driver #NBIF

  4. Az AMD már készíti a nyílt AMDGPU drivert GDDR7-hez, ami RDNA5-re utal. Új patchek (GDDR7, IH8.0, NBIF7.10) erősítik az előkészületeket — mit jelent ez neked Linuxon? Te szerinted időben kész lesz a kernel?

    linuxmint.hu/hir/2026/09/amd-e

    #AMD #RDNA5 #GDDR7 #AMDGPU #Linux #kernel #driver #NBIF

  5. RT @pupposandro: Was hältst du von der neuen @AMD RX 10800XT, die auf der Mikroarchitektur RDNA 5 basiert und bald erscheint? Insider-Lecks schreiben dem Chip gigantische Spezifikationen zu: bis zu 200 Compute Units (CU), ein massiver 512-Bit-Bus, bis zu 48 GB schnellen GDDR7-Speicher und Taktfrequenzen im Bereich t.co/agSeHjf2sS

    mehr auf Arint.info

    #AMD #GDDR7 #GPU #RDNA5 #RX10800XT #TechNews #arint_info

    https://x.com/pupposandro/status/2101603671146406019

  6. RT @pupposandro: Was hältst du von der neuen @AMD RX 10800XT, die auf der Mikroarchitektur RDNA 5 basiert und bald erscheint? Insider-Lecks schreiben dem Chip gigantische Spezifikationen zu: bis zu 200 Compute Units (CU), ein massiver 512-Bit-Bus, bis zu 48 GB schnellen GDDR7-Speicher und Taktfrequenzen im Bereich t.co/agSeHjf2sS

    mehr auf Arint.info

    #AMD #GDDR7 #GPU #RDNA5 #RX10800XT #TechNews #arint_info

    https://x.com/pupposandro/status/2101603671146406019

  7. RT @pupposandro: Was hältst du von der neuen @AMD RX 10800XT, die auf der Mikroarchitektur RDNA 5 basiert und bald erscheint? Insider-Lecks schreiben dem Chip gigantische Spezifikationen zu: bis zu 200 Compute Units (CU), ein massiver 512-Bit-Bus, bis zu 48 GB schnellen GDDR7-Speicher und Taktfrequenzen im Bereich t.co/agSeHjf2sS

    mehr auf Arint.info

    #AMD #GDDR7 #GPU #RDNA5 #RX10800XT #TechNews #arint_info

    https://x.com/pupposandro/status/2101603671146406019

  8. RT @pupposandro: Was hältst du von der neuen @AMD RX 10800XT, die auf der Mikroarchitektur RDNA 5 basiert und bald erscheint? Insider-Lecks schreiben dem Chip gigantische Spezifikationen zu: bis zu 200 Compute Units (CU), ein massiver 512-Bit-Bus, bis zu 48 GB schnellen GDDR7-Speicher und Taktfrequenzen im Bereich t.co/agSeHjf2sS

    mehr auf Arint.info

    #AMD #GDDR7 #GPU #RDNA5 #RX10800XT #TechNews #arint_info

    https://x.com/pupposandro/status/2101603671146406019

  9. RT @pupposandro: Was hältst du von der neuen @AMD RX 10800XT, die auf der Mikroarchitektur RDNA 5 basiert und bald erscheint? Insider-Lecks schreiben dem Chip gigantische Spezifikationen zu: bis zu 200 Compute Units (CU), ein massiver 512-Bit-Bus, bis zu 48 GB schnellen GDDR7-Speicher und Taktfrequenzen im Bereich t.co/agSeHjf2sS

    mehr auf Arint.info

    #AMD #GDDR7 #GPU #RDNA5 #RX10800XT #TechNews #arint_info

    https://x.com/pupposandro/status/2101603671146406019

  10. NVIDIA sold the RTX 5060 Ti with 8GB or 16GB. Same chip. Launch price difference: $50.
    Today the market difference is $191.
    The 4060 Ti ran the same experiment two years earlier and landed within 50 cents per gigabyte.

    buysellram.com/blog/nvidia-con

    #NVIDIA #GPUPrices #RTX50 #RTX5090 #VRAM #GDDR7 #DRAM #GPU #PCHardware #ITAD #ITAssetDisposition #DataCenter #ResaleValue #technology

  11. NVIDIA sold the RTX 5060 Ti with 8GB or 16GB. Same chip. Launch price difference: $50.
    Today the market difference is $191.
    The 4060 Ti ran the same experiment two years earlier and landed within 50 cents per gigabyte.

    buysellram.com/blog/nvidia-con

    #NVIDIA #GPUPrices #RTX50 #RTX5090 #VRAM #GDDR7 #DRAM #GPU #PCHardware #ITAD #ITAssetDisposition #DataCenter #ResaleValue #technology

  12. NVIDIA sold the RTX 5060 Ti with 8GB or 16GB. Same chip. Launch price difference: $50.
    Today the market difference is $191.
    The 4060 Ti ran the same experiment two years earlier and landed within 50 cents per gigabyte.

    buysellram.com/blog/nvidia-con

    #NVIDIA #GPUPrices #RTX50 #RTX5090 #VRAM #GDDR7 #DRAM #GPU #PCHardware #ITAD #ITAssetDisposition #DataCenter #ResaleValue #technology

  13. NVIDIA sold the RTX 5060 Ti with 8GB or 16GB. Same chip. Launch price difference: $50.
    Today the market difference is $191.
    The 4060 Ti ran the same experiment two years earlier and landed within 50 cents per gigabyte.

    buysellram.com/blog/nvidia-con

    #NVIDIA #GPUPrices #RTX50 #RTX5090 #VRAM #GDDR7 #DRAM #GPU #PCHardware #ITAD #ITAssetDisposition #DataCenter #ResaleValue

  14. NVIDIA sold the RTX 5060 Ti with 8GB or 16GB. Same chip. Launch price difference: $50.
    Today the market difference is $191.
    The 4060 Ti ran the same experiment two years earlier and landed within 50 cents per gigabyte.

    buysellram.com/blog/nvidia-con

    #NVIDIA #GPUPrices #RTX50 #RTX5090 #VRAM #GDDR7 #DRAM #GPU #PCHardware #ITAD #ITAssetDisposition #DataCenter #ResaleValue

  15. NVIDIA sold the RTX 5060 Ti with 8GB or 16GB. Same chip. Launch price difference: $50.
    Today the market difference is $191.
    The 4060 Ti ran the same experiment two years earlier and landed within 50 cents per gigabyte.

    buysellram.com/blog/nvidia-con

    #NVIDIA #GPUPrices #RTX50 #RTX5090 #VRAM #GDDR7 #DRAM #GPU #PCHardware #ITAD #ITAssetDisposition #DataCenter #ResaleValue

  16. NVIDIA sold the RTX 5060 Ti with 8GB or 16GB. Same chip. Launch price difference: $50.
    Today the market difference is $191.
    The 4060 Ti ran the same experiment two years earlier and landed within 50 cents per gigabyte.

    buysellram.com/blog/nvidia-con

    #NVIDIA #GPUPrices #RTX50 #RTX5090 #VRAM #GDDR7 #DRAM #GPU #PCHardware #ITAD #ITAssetDisposition #DataCenter #ResaleValue

  17. buysellram.com/blog/nvidia-con

    Two findings from the August 2026 NVIDIA GPU price data.

    First: memory capacity rather than performance tier is setting the premium over MSRP. Nothing with 8GB or 12GB lists more than 13% above launch price. Nothing with 16GB or more lists less than 18% above it. The band between is empty — and the RTX 5060 Ti 16GB, the cheapest card in the upper group, carries a larger premium than the RTX 5080.

    The cleanest evidence comes from the pairs where the same GPU shipped in two memory configurations. On the RTX 5060 Ti, the extra 8GB costs $191 in the market: $23.88 per gigabyte, against $6.25 at launch and roughly $10 for the GDDR7 modules themselves. The RTX 4060 Ti, launched two years earlier, lands at $24.38.

    Second: across the RTX 50 line, used cards now list 0–14% below new, three of them at zero. The RTX 40 generation, measured the same day, still lists 11–36% below.

    #NVIDIA #GPUPrices #RTX50 #RTX5090 #VRAM #GDDR7 #DRAM #GPU #PCHardware #ITAD #ITAssetDisposition #DataCenter #ResaleValue

  18. buysellram.com/blog/nvidia-con

    Two findings from the August 2026 NVIDIA GPU price data.

    First: memory capacity rather than performance tier is setting the premium over MSRP. Nothing with 8GB or 12GB lists more than 13% above launch price. Nothing with 16GB or more lists less than 18% above it. The band between is empty — and the RTX 5060 Ti 16GB, the cheapest card in the upper group, carries a larger premium than the RTX 5080.

    The cleanest evidence comes from the pairs where the same GPU shipped in two memory configurations. On the RTX 5060 Ti, the extra 8GB costs $191 in the market: $23.88 per gigabyte, against $6.25 at launch and roughly $10 for the GDDR7 modules themselves. The RTX 4060 Ti, launched two years earlier, lands at $24.38.

    Second: across the RTX 50 line, used cards now list 0–14% below new, three of them at zero. The RTX 40 generation, measured the same day, still lists 11–36% below.

  19. NVIDIA sold the RTX 5060 Ti with 8GB or 16GB. Same chip. Launch price difference: $50.
    Today the market difference is $191.
    The 4060 Ti ran the same experiment two years earlier and landed within 50 cents per gigabyte.

    buysellram.com/blog/nvidia-con

    #NVIDIA #GPUPrices #RTX50 #RTX5090 #VRAM #GDDR7 #DRAM #GPU #PCHardware #ITAD #ITAssetDisposition #DataCenter #ResaleValue #tech

  20. NVIDIA sold the RTX 5060 Ti with 8GB or 16GB. Same chip. Launch price difference: $50.
    Today the market difference is $191.
    The 4060 Ti ran the same experiment two years earlier and landed within 50 cents per gigabyte.

    buysellram.com/blog/nvidia-con

    #NVIDIA #GPUPrices #RTX50 #RTX5090 #VRAM #GDDR7 #DRAM #GPU #PCHardware #ITAD #ITAssetDisposition #DataCenter #ResaleValue #tech

  21. NVIDIA sold the RTX 5060 Ti with 8GB or 16GB. Same chip. Launch price difference: $50.
    Today the market difference is $191.
    The 4060 Ti ran the same experiment two years earlier and landed within 50 cents per gigabyte.

    buysellram.com/blog/nvidia-con

    #NVIDIA #GPUPrices #RTX50 #RTX5090 #VRAM #GDDR7 #DRAM #GPU #PCHardware #ITAD #ITAssetDisposition #DataCenter #ResaleValue #tech

  22. NVIDIA sold the RTX 5060 Ti with 8GB or 16GB. Same chip. Launch price difference: $50.
    Today the market difference is $191.
    The 4060 Ti ran the same experiment two years earlier and landed within 50 cents per gigabyte.

    buysellram.com/blog/nvidia-con

    #NVIDIA #GPUPrices #RTX50 #RTX5090 #VRAM #GDDR7 #DRAM #GPU #PCHardware #ITAD #ITAssetDisposition #DataCenter #ResaleValue #tech

  23. NVIDIA sold the RTX 5060 Ti with 8GB or 16GB. Same chip. Launch price difference: $50.
    Today the market difference is $191.
    The 4060 Ti ran the same experiment two years earlier and landed within 50 cents per gigabyte.

    buysellram.com/blog/nvidia-con

    #NVIDIA #GPUPrices #RTX50 #RTX5090 #VRAM #GDDR7 #DRAM #GPU #PCHardware #ITAD #ITAssetDisposition #DataCenter #ResaleValue #tech

  24. Nvidia has reportedly told board partners that GPU kit prices are rising, and this round covers GDDR6 cards, not just GDDR7 Blackwell parts. AMD raised its own kit prices roughly 10% three weeks earlier. Memory cost is now moving the entire GPU stack. Older workstation cards sitting in decommissioned fleets are worth a quote before they hit the scrap pile.
    #GPUPrices #Nvidia #AMD #GDDR7 #GDDR6 #MemoryShortage #DRAM #GraphicsCards #DataCenter #PCHardware
    wccftech.com/nvidia-reportedly

  25. Nvidia has reportedly told board partners that GPU kit prices are rising, and this round covers GDDR6 cards, not just GDDR7 Blackwell parts. AMD raised its own kit prices roughly 10% three weeks earlier. Memory cost is now moving the entire GPU stack. Older workstation cards sitting in decommissioned fleets are worth a quote before they hit the scrap pile.
    #GPUPrices #Nvidia #AMD #GDDR7 #GDDR6 #MemoryShortage #DRAM #GraphicsCards #DataCenter #PCHardware
    wccftech.com/nvidia-reportedly

  26. Angeblich hat #Nvidia eine #Preiserhöhung bei GPU-Kits vorgenommen. Grund dafür sind steigende Kosten für #GDDR6- und #GDDR7-#Speicher. Gamer müssen sich wohl auf noch teurere #GeForce-#Grafikkarten einstellen. winfuture.de/news,160185.html?

  27. Angeblich hat #Nvidia eine #Preiserhöhung bei GPU-Kits vorgenommen. Grund dafür sind steigende Kosten für #GDDR6- und #GDDR7-#Speicher. Gamer müssen sich wohl auf noch teurere #GeForce-#Grafikkarten einstellen. winfuture.de/news,160185.html?

  28. Angeblich hat #Nvidia eine #Preiserhöhung bei GPU-Kits vorgenommen. Grund dafür sind steigende Kosten für #GDDR6- und #GDDR7-#Speicher. Gamer müssen sich wohl auf noch teurere #GeForce-#Grafikkarten einstellen. winfuture.de/news,160185.html?

  29. Angeblich hat #Nvidia eine #Preiserhöhung bei GPU-Kits vorgenommen. Grund dafür sind steigende Kosten für #GDDR6- und #GDDR7-#Speicher. Gamer müssen sich wohl auf noch teurere #GeForce-#Grafikkarten einstellen. winfuture.de/news,160185.html?

  30. Angeblich hat #Nvidia eine #Preiserhöhung bei GPU-Kits vorgenommen. Grund dafür sind steigende Kosten für #GDDR6- und #GDDR7-#Speicher. Gamer müssen sich wohl auf noch teurere #GeForce-#Grafikkarten einstellen. winfuture.de/news,160185.html?

  31. Segmentations et rareté : le marché du GPU en mai 2026

    Why is the RTX 5070 Ti 16GB hard to find in stores on May 24, 2026? NVIDIA's new graphics cards are confusing to buy due to low stock and many similar models.

    #RTX5070Ti #NVIDIAGPU #GraphicsCardShortage #GDDR7 #PCGaming2026

    newsletter.tf/nvidia-rtx-5070-

  32. Buying a new NVIDIA RTX 50 series graphics card is harder now than before. The top RTX 5070 Ti 16GB is only sold in physical stores from May 24, 2026. Other cards have many confusing names.

    #RTX5070Ti #NVIDIAGPU #GraphicsCardShortage #GDDR7 #PCGaming2026
    newsletter.tf/nvidia-rtx-5070-

  33. Nvidia implemented a $300 wholesale price hike on the RTX 5090 effective May 13 — passed directly to board partners like ASUS, MSI, and Gigabyte. The official MSRP stays at $1,999, but that card is effectively impossible to buy at that price. Most configurations are now trading above $4,000.
    The root cause isn't arbitrary. GDDR7 memory — which the RTX 5090 uses 32GB of — now makes up over 80% of the card's total bill of materials. AI data centers are consuming foundry wafer capacity at scale, pushing memory costs up across the board. Nvidia has also cut RTX 50 series production by up to 40% and canceled the RTX 50 Super entirely, pushing the RTX 60 generation to 2028.
    For enterprise teams weighing hardware investments: local GPU acquisition still beats cloud compute on TCO for sustained workloads — but the math is changing fast. And legacy GPU inventory is worth more right now than it's been in years.
    Full breakdown linked below.

    #Nvidia #RTX5090 #GPU #GDDR7 #ITAssetManagement #ITAD #HardwarePricing #TechInfrastructure #AIInfrastructure #DataCenter #PCHardware #EnterpriseIT #BuySellRam #technology

  34. Nvidia implemented a $300 wholesale price hike on the RTX 5090 effective May 13 — passed directly to board partners like ASUS, MSI, and Gigabyte. The official MSRP stays at $1,999, but that card is effectively impossible to buy at that price. Most configurations are now trading above $4,000.
    The root cause isn't arbitrary. GDDR7 memory — which the RTX 5090 uses 32GB of — now makes up over 80% of the card's total bill of materials. AI data centers are consuming foundry wafer capacity at scale, pushing memory costs up across the board. Nvidia has also cut RTX 50 series production by up to 40% and canceled the RTX 50 Super entirely, pushing the RTX 60 generation to 2028.
    For enterprise teams weighing hardware investments: local GPU acquisition still beats cloud compute on TCO for sustained workloads — but the math is changing fast. And legacy GPU inventory is worth more right now than it's been in years.
    Full breakdown linked below.

    #Nvidia #RTX5090 #GPU #GDDR7 #ITAssetManagement #ITAD #HardwarePricing #TechInfrastructure #AIInfrastructure #DataCenter #PCHardware #EnterpriseIT #BuySellRam #technology

  35. Nvidia implemented a $300 wholesale price hike on the RTX 5090 effective May 13 — passed directly to board partners like ASUS, MSI, and Gigabyte. The official MSRP stays at $1,999, but that card is effectively impossible to buy at that price. Most configurations are now trading above $4,000.
    The root cause isn't arbitrary. GDDR7 memory — which the RTX 5090 uses 32GB of — now makes up over 80% of the card's total bill of materials. AI data centers are consuming foundry wafer capacity at scale, pushing memory costs up across the board. Nvidia has also cut RTX 50 series production by up to 40% and canceled the RTX 50 Super entirely, pushing the RTX 60 generation to 2028.
    For enterprise teams weighing hardware investments: local GPU acquisition still beats cloud compute on TCO for sustained workloads — but the math is changing fast. And legacy GPU inventory is worth more right now than it's been in years.
    Full breakdown linked below.

    #Nvidia #RTX5090 #GPU #GDDR7 #ITAssetManagement #ITAD #HardwarePricing #TechInfrastructure #AIInfrastructure #DataCenter #PCHardware #EnterpriseIT #BuySellRam #technology

  36. Nvidia implemented a $300 wholesale price hike on the RTX 5090 effective May 13 — passed directly to board partners like ASUS, MSI, and Gigabyte. The official MSRP stays at $1,999, but that card is effectively impossible to buy at that price. Most configurations are now trading above $4,000.
    The root cause isn't arbitrary. GDDR7 memory — which the RTX 5090 uses 32GB of — now makes up over 80% of the card's total bill of materials. AI data centers are consuming foundry wafer capacity at scale, pushing memory costs up across the board. Nvidia has also cut RTX 50 series production by up to 40% and canceled the RTX 50 Super entirely, pushing the RTX 60 generation to 2028.
    For enterprise teams weighing hardware investments: local GPU acquisition still beats cloud compute on TCO for sustained workloads — but the math is changing fast. And legacy GPU inventory is worth more right now than it's been in years.
    Full breakdown linked below.

    #Nvidia #RTX5090 #GPU #GDDR7 #ITAssetManagement #ITAD #HardwarePricing #TechInfrastructure #AIInfrastructure #DataCenter #PCHardware #EnterpriseIT #BuySellRam #technology

  37. Nvidia implemented a $300 wholesale price hike on the RTX 5090 effective May 13 — passed directly to board partners like ASUS, MSI, and Gigabyte. The official MSRP stays at $1,999, but that card is effectively impossible to buy at that price. Most configurations are now trading above $4,000.
    The root cause isn't arbitrary. GDDR7 memory — which the RTX 5090 uses 32GB of — now makes up over 80% of the card's total bill of materials. AI data centers are consuming foundry wafer capacity at scale, pushing memory costs up across the board. Nvidia has also cut RTX 50 series production by up to 40% and canceled the RTX 50 Super entirely, pushing the RTX 60 generation to 2028.
    For enterprise teams weighing hardware investments: local GPU acquisition still beats cloud compute on TCO for sustained workloads — but the math is changing fast. And legacy GPU inventory is worth more right now than it's been in years.
    Full breakdown linked below.

    #Nvidia #RTX5090 #GPU #GDDR7 #ITAssetManagement #ITAD #HardwarePricing #TechInfrastructure #AIInfrastructure #DataCenter #PCHardware #EnterpriseIT #BuySellRam #technology