Very bad performance in VM vs bare metal

Hello, I have been using VFIO for years but it had been a long time since I gamed on it.

I recently discovered Hell Let Loose and wanted to play, so I tried.

My performance seems really bad on VFIO vs bare metal, I might be getting 50% of the bare metal performance when virtualized.

I am on Arch Linux 5.16.5-arch1-1.

I tried to update some stuff in my setup to no avail. I am attaching my xml in case anyone can help.
I am on the Asrock Taichi X399 with the 2920X Threadripper, 4x8GB of RAM and a GTX 1070 for the guest. I am also passing through an Intel X520 NIC and a USB controller, as well as the VM SSD.

<domain type="kvm">
  <name>wingaming</name>
  <uuid>ffaeedcb-67f8-40b8-8541-918aa9a32c26</uuid>
  <memory unit="KiB">12288000</memory>
  <currentMemory unit="KiB">12288000</currentMemory>
  <vcpu placement="static">12</vcpu>
  <cputune>
    <vcpupin vcpu="0" cpuset="6"/>
    <vcpupin vcpu="1" cpuset="18"/>
    <vcpupin vcpu="2" cpuset="7"/>
    <vcpupin vcpu="3" cpuset="19"/>
    <vcpupin vcpu="4" cpuset="8"/>
    <vcpupin vcpu="5" cpuset="20"/>
    <vcpupin vcpu="6" cpuset="9"/>
    <vcpupin vcpu="7" cpuset="21"/>
    <vcpupin vcpu="8" cpuset="10"/>
    <vcpupin vcpu="9" cpuset="22"/>
    <vcpupin vcpu="10" cpuset="11"/>
    <vcpupin vcpu="11" cpuset="23"/>
  </cputune>
  <numatune>
    <memory mode="strict" nodeset="1"/>
  </numatune>
  <os>
    <type arch="x86_64" machine="pc-q35-6.2">hvm</type>
    <loader readonly="yes" type="pflash">/usr/share/ovmf/x64/OVMF_CODE.fd</loader>
    <nvram>/var/lib/libvirt/qemu/nvram/win30_VARS.fd</nvram>
    <bootmenu enable="no"/>
  </os>
  <features>
    <acpi/>
    <apic/>
    <vmport state="off"/>
    <ioapic driver="kvm"/>
  </features>
  <cpu mode="host-passthrough" check="none" migratable="on">
    <topology sockets="1" dies="1" cores="6" threads="2"/>
    <feature policy="require" name="topoext"/>
  </cpu>
  <clock offset="localtime">
    <timer name="rtc" tickpolicy="catchup"/>
    <timer name="pit" tickpolicy="delay"/>
    <timer name="hpet" present="no"/>
    <timer name="hypervclock" present="yes"/>
  </clock>
  <on_poweroff>destroy</on_poweroff>
  <on_reboot>restart</on_reboot>
  <on_crash>destroy</on_crash>
  <pm>
    <suspend-to-mem enabled="no"/>
    <suspend-to-disk enabled="no"/>
  </pm>
  <devices>
    <emulator>/usr/bin/qemu-system-x86_64</emulator>
    <disk type="file" device="cdrom">
      <driver name="qemu" type="raw"/>
      <source file="/home/Downloads/isos/virtio-win-0.1.215.iso"/>
      <target dev="sdb" bus="sata"/>
      <readonly/>
      <address type="drive" controller="0" bus="0" target="0" unit="1"/>
    </disk>
    <disk type="block" device="disk">
      <driver name="qemu" type="raw" cache="none" io="native"/>
      <source dev="/dev/disk/by-id/ata-SAMSUNG_MZ7TD128HAFV-000L1_S14TNSADA27642"/>
      <target dev="vda" bus="virtio"/>
      <boot order="1"/>
      <address type="pci" domain="0x0000" bus="0x05" slot="0x00" function="0x0"/>
    </disk>
    <controller type="usb" index="0" model="qemu-xhci" ports="15">
      <address type="pci" domain="0x0000" bus="0x02" slot="0x00" function="0x0"/>
    </controller>
    <controller type="pci" index="0" model="pcie-root"/>
    <controller type="pci" index="1" model="pcie-root-port">
      <model name="pcie-root-port"/>
      <target chassis="1" port="0x10"/>
      <address type="pci" domain="0x0000" bus="0x00" slot="0x02" function="0x0" multifunction="on"/>
    </controller>
    <controller type="pci" index="2" model="pcie-root-port">
      <model name="pcie-root-port"/>
      <target chassis="2" port="0x11"/>
      <address type="pci" domain="0x0000" bus="0x00" slot="0x02" function="0x1"/>
    </controller>
    <controller type="pci" index="3" model="pcie-root-port">
      <model name="pcie-root-port"/>
      <target chassis="3" port="0x12"/>
      <address type="pci" domain="0x0000" bus="0x00" slot="0x02" function="0x2"/>
    </controller>
    <controller type="pci" index="4" model="pcie-root-port">
      <model name="pcie-root-port"/>
      <target chassis="4" port="0x13"/>
      <address type="pci" domain="0x0000" bus="0x00" slot="0x02" function="0x3"/>
    </controller>
    <controller type="pci" index="5" model="pcie-root-port">
      <model name="pcie-root-port"/>
      <target chassis="5" port="0x14"/>
      <address type="pci" domain="0x0000" bus="0x00" slot="0x02" function="0x4"/>
    </controller>
    <controller type="pci" index="6" model="pcie-root-port">
      <model name="pcie-root-port"/>
      <target chassis="6" port="0x15"/>
      <address type="pci" domain="0x0000" bus="0x00" slot="0x02" function="0x5"/>
    </controller>
    <controller type="pci" index="7" model="pcie-root-port">
      <model name="pcie-root-port"/>
      <target chassis="7" port="0x16"/>
      <address type="pci" domain="0x0000" bus="0x00" slot="0x02" function="0x6"/>
    </controller>
    <controller type="pci" index="9" model="pcie-root-port">
      <model name="pcie-root-port"/>
      <target chassis="9" port="0x17"/>
      <address type="pci" domain="0x0000" bus="0x00" slot="0x02" function="0x7"/>
    </controller>
    <controller type="pci" index="10" model="pcie-root-port">
      <model name="pcie-root-port"/>
      <target chassis="10" port="0x18"/>
      <address type="pci" domain="0x0000" bus="0x00" slot="0x03" function="0x0" multifunction="on"/>
    </controller>
    <controller type="pci" index="11" model="pcie-root-port">
      <model name="pcie-root-port"/>
      <target chassis="11" port="0x19"/>
      <address type="pci" domain="0x0000" bus="0x00" slot="0x03" function="0x1"/>
    </controller>
    <controller type="pci" index="12" model="pcie-root-port">
      <model name="pcie-root-port"/>
      <target chassis="12" port="0x1a"/>
      <address type="pci" domain="0x0000" bus="0x00" slot="0x03" function="0x2"/>
    </controller>
    <controller type="pci" index="13" model="pcie-root-port">
      <model name="pcie-root-port"/>
      <target chassis="13" port="0x1b"/>
      <address type="pci" domain="0x0000" bus="0x00" slot="0x03" function="0x3"/>
    </controller>
    <controller type="pci" index="14" model="pcie-root-port">
      <model name="pcie-root-port"/>
      <target chassis="14" port="0x1c"/>
      <address type="pci" domain="0x0000" bus="0x00" slot="0x03" function="0x4"/>
    </controller>
    <controller type="pci" index="15" model="pcie-root-port">
      <model name="pcie-root-port"/>
      <target chassis="15" port="0x1d"/>
      <address type="pci" domain="0x0000" bus="0x00" slot="0x03" function="0x5"/>
    </controller>
    <controller type="scsi" index="0" model="virtio-scsi">
      <address type="pci" domain="0x0000" bus="0x0a" slot="0x00" function="0x0"/>
    </controller>
    <controller type="sata" index="0">
      <address type="pci" domain="0x0000" bus="0x00" slot="0x1f" function="0x2"/>
    </controller>
    <controller type="pci" index="8" model="pcie-root-port">
      <model name="pcie-root-port"/>
      <target chassis="8" port="0x8"/>
      <address type="pci" domain="0x0000" bus="0x00" slot="0x01" function="0x0" multifunction="on"/>
    </controller>
    <controller type="pci" index="16" model="pcie-root-port">
      <model name="pcie-root-port"/>
      <target chassis="16" port="0x9"/>
      <address type="pci" domain="0x0000" bus="0x00" slot="0x01" function="0x1"/>
    </controller>
    <controller type="pci" index="17" model="pcie-to-pci-bridge">
      <model name="pcie-pci-bridge"/>
      <address type="pci" domain="0x0000" bus="0x01" slot="0x00" function="0x0"/>
    </controller>
    <input type="mouse" bus="ps2"/>
    <input type="keyboard" bus="ps2"/>
    <graphics type="spice" autoport="yes">
      <listen type="address"/>
      <image compression="off"/>
      <gl enable="no"/>
    </graphics>
    <sound model="ich9">
      <codec type="micro"/>
      <audio id="1"/>
      <address type="pci" domain="0x0000" bus="0x00" slot="0x1b" function="0x0"/>
    </sound>
    <audio id="1" type="pulseaudio" serverName="/run/user/1000/pulse/native">
      <input mixingEngine="no"/>
      <output mixingEngine="no"/>
    </audio>
    <video>
      <model type="none"/>
    </video>
    <hostdev mode="subsystem" type="pci" managed="yes">
      <source>
        <address domain="0x0000" bus="0x43" slot="0x00" function="0x0"/>
      </source>
      <address type="pci" domain="0x0000" bus="0x03" slot="0x00" function="0x0"/>
    </hostdev>
    <hostdev mode="subsystem" type="pci" managed="yes">
      <source>
        <address domain="0x0000" bus="0x43" slot="0x00" function="0x1"/>
      </source>
      <address type="pci" domain="0x0000" bus="0x04" slot="0x00" function="0x0"/>
    </hostdev>
    <hostdev mode="subsystem" type="pci" managed="yes">
      <source>
        <address domain="0x0000" bus="0x41" slot="0x00" function="0x0"/>
      </source>
      <address type="pci" domain="0x0000" bus="0x06" slot="0x00" function="0x0"/>
    </hostdev>
    <hostdev mode="subsystem" type="pci" managed="yes">
      <source>
        <address domain="0x0000" bus="0x41" slot="0x00" function="0x1"/>
      </source>
      <address type="pci" domain="0x0000" bus="0x0e" slot="0x00" function="0x0"/>
    </hostdev>
    <hostdev mode="subsystem" type="pci" managed="yes">
      <source>
        <address domain="0x0000" bus="0x44" slot="0x00" function="0x3"/>
      </source>
      <address type="pci" domain="0x0000" bus="0x0b" slot="0x00" function="0x0"/>
    </hostdev>
    <redirdev bus="usb" type="spicevmc">
      <address type="usb" bus="0" port="4"/>
    </redirdev>
    <memballoon model="none"/>
    <shmem name="looking-glass">
      <model type="ivshmem-plain"/>
      <size unit="M">256</size>
      <address type="pci" domain="0x0000" bus="0x11" slot="0x01" function="0x0"/>
    </shmem>
  </devices>
</domain>

Did you find the answer?
I also find I loose about 20% CPU performance within KVM.