AMD Radeon RX 6700 XT

Official identity

Card

AMD Radeon RX 6700 XT

gfx

gfx1031

Published VRAM

12 GB

Hardware label, not a bench

ROCm matrix

Unofficial

Navi 22 / RX 67xx is gfx1031. Not the official gfx1030 W6800 row on the current Radeon ROCm matrix. Community HIP/Vulkan paths exist. Prefer Vulkan llama.cpp if HIP is angry. See the gfx1031 HSA_OVERRIDE note.

Cited support row: ROCm 10.1.0 compatibility matrix and Linux system requirements. We do not invent a support claim past that listing. AMD product page: RX 6700 XT.

HSA_OVERRIDE: Community threads document HSA_OVERRIDE_GFX_VERSION=10.3.0 so gfx1030 objects load on gfx1031. Unofficial. Prefer Vulkan llama.cpp if HIP is angry.

What fits on this card (256K context)

Shopper verdict at 4K, then follow the pair page for 32K and full context. Q4 and up. No printed prices.

What fits in VRAM

Qwen3.6-35B-A3B on llama.cpp, f16 KV, one GPU. Q6 / Q5 / Q4 rows are calculator estimates. UD-Q3_K_XL is a labeled estimate (Hugging Face listing for Qwen3.6-35B-A3B-UD-Q3_K_XL.gguf (16.8 GB)) — not a local desktop run. Speed stays not measured. Change quant or context in the calculator.

Weights notes: Q6_K — 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. Q5_K_M — Hugging Face listing for Qwen3.6-35B-A3B-UD-Q5_K_XL.gguf (26.6 GB). Converted 26.6 × 10⁹ bytes → GiB. Not measured VRAM. Q4_K_M — Estimate: total_params × 4.85 bpw (nominal GGUF Q4_K_M) / 8. Active params do not shrink the file. UD-Q3_K_XL — Hugging Face listing for Qwen3.6-35B-A3B-UD-Q3_K_XL.gguf (16.8 GB). Converted 16.8 × 10⁹ bytes → GiB. Not measured VRAM.

System RAM

Minimum system RAM needed and RAM needed at full context for Qwen3.6-35B-A3B on llama.cpp at Q4_K_M, 32K selected and the model’s full context. Estimate until a first-party amdai-bench/run@1 card exists for this SKU. Rounded up to a real DIMM kit.

llama.cpp-first stack

1. Step 1

   llama.cpp first

   Vulkan is the consumer default on this site. HIP is unofficial on this gfx1031 consumer card — the current Radeon official row lists W6800 (gfx1030), not the 6700 XT. Prefer Vulkan llama.cpp if HIP is angry. Ollama and vLLM are not the house path for this card.

2. Step 2

   gfx1031, not gfx1030

   gfx1031 is Navi 22 / RX 67xx. Do not mix a gfx1030 (6800 XT / W6800), gfx110x (7900 / 7800 / 7700 / 7600), or gfx1201 (R9700 / 9070 XT) install. Community HSA_OVERRIDE=10.3.0 is unofficial. Re-check the cited matrix and the gfx1031 problem note before you install.

3. Step 3

   12 GB XT, not the 16 GB 6800 XT

   This sheet sizes the 12 GB consumer 6700 XT. AMD product page: 12 GB GDDR6, RDNA 2, 230 W typical board power. House 35B Q4–Q6 files do not fit this VRAM — expect RAM offload or a lighter listed Q3 file, both estimates. The 16 GB 6800 XT and the 10 GB non-XT 6700 are different listings. Size the file on the calculator before you download.

4. Step 4

   Setup, then Stack Lab doctor

   First-run setup is Ubuntu. Open Stack Lab doctor for the install family rocminfo actually prints. House daily and Flash profiles are R9700 / local desktop — they do not apply to this 12 GB card. Packages are not published yet.

Compare with…

Head-to-head pages use the same VRAM, bandwidth, and calculator fit already on the sheets. Q3 is a labeled estimate. No invented prices. RX 6700 XT against the other published sheets:

• Compare GPUs
• vs RX 6800 XT
• vs RX 7700 XT

Also: PRO W6800 · PRO W7700 · PRO W7800 · PRO W7900 · R9700 · RX 6950 XT · RX 7600 · RX 7600 XT · RX 7800 XT · RX 7900 GRE · RX 7900 XT · RX 7900 XTX · RX 9060 XT · RX 9070 · RX 9070 GRE · RX 9070 XT · Strix Halo