PRO W7900 vs PRO W6800 for local AI

VRAM, bandwidth, gfx

Which 35B quants fit

Qwen3.6-35B-A3B on llama.cpp, f16 KV. Totals are calculator estimates. Speed is measured only on the R9700 cells that already exist; everything else stays not measured. UD-Q3_K_XL is always a labeled estimate.

Weights file Estimate: total_params × 6.56 bpw (nominal GGUF Q6_K; UD-Q6_K_XL uses the same bucket) / 8. Active params do not shrink the file.. Same GGUF on both cards.

System RAM

When a house 35B Q4 file does not fit, the spill is system RAM. Shopper lines stay Minimum system RAM needed and RAM needed at full context for Qwen3.6-35B-A3B at llama.cpp, Q4_K_M, 32K selected and the model’s full context. Estimate unless a measured R9700 card overlays the kit. If both sides fit, those labels still name the calculator lines if you raise context or a larger quant.

ROCm and Vulkan

1. Note 1

   llama.cpp first

   Vulkan llama.cpp is the consumer default. HIP when rocminfo lists the gfx on this page. Ollama and vLLM are not the house path on these sheets.

2. Note 2

   Different gfx family packages

   PRO W7900 needs the gfx1100 family package (48 GB workstation. Dual-slot sibling is also listed.) PRO W6800 needs gfx1030 (Older but still listed on the 10.1 matrix.) Do not mix those pins.

3. Note 3

   Cited support rows

   PRO W7900: official — 48 GB workstation. Dual-slot sibling is also listed. PRO W6800: official — Older but still listed on the 10.1 matrix.

Cited rows: ROCm 10.1.0 compatibility matrix and Linux system requirements. More gfx notes on /rocm/gfx.

Plain-English pick

• Chat

  Both cards hold house 35B Q4_K_M at 4K on the calculator. Neither side has a local desktop tok/s. Pick on VRAM headroom and the gfx package you can install, not a speed we invent.

• Coding agents

  Keep llama.cpp first. The side that holds Q4 in VRAM (PRO W7900 and PRO W6800) is the less painful coding-agent host. House Flash / agent pins stay R9700 / local desktop — they do not transfer. No invented agent speed.

• Long context

  KV grows with context. Q4 at 32K fits PRO W7900 and fits PRO W6800 on the calculator. Read the long-context guide for the measured R9700 128K–262K cards. We do not invent a 128K tok/s here.

• Image gen

  Image gen on AMDai is ComfyUI / HIP PyTorch, not llama.cpp. PRO W7900 is the 32 GB discrete class; PRO W6800 is the 32 GB discrete class. Seconds-per-image stay not yet measured by AMDai. Start smaller (SD 1.5) on 8 / 12 / 16 GB class cards. Flux-class is tighter than SDXL. Size the checkpoint on the image-gen guide — do not copy a tok/s from the LLM table.

Check price

Affiliate hops only. No live or invented street price. Same disclosure as every other sheet.