GPU directory · Radeon RX · RDNA 3 · gfx1100
Cited, not measured on the local desktop
AMD Radeon RX 7900 XTX
24 GB gfx1100 RDNA 3 — the 7900 XTX, not the 20 GB 7900 XT. AMD product page cites 24 GB GDDR6, RDNA 3, and 355 W typical board power. Official on the cited ROCm 10.1 matrix as gfx1100; install the gfx110x family package, not the gfx1201 pin used on the measured R9700. Size Qwen3.6-35B-A3B on the calculator before you assume a Q5 file sits in VRAM at long context. Buy the R9700 when you want measured 32 GB recipes. Not a measured local desktop card.
If the app is not installed, packages are not published yet. There is no public download URL. Read the Stack Lab install notes . If Stack Lab is already running on this machine, open the local app .
How we test — Measured cells cite official amdai-bench/run@1 cards. Estimates stay labeled. Q3 is estimate-only. Q1/Q2 stay off.
Official identity
- Card
- AMD Radeon RX 7900 XTX
- gfx
- gfx1100
- Published VRAM
- 24 GB
- Hardware label, not a bench
- ROCm matrix
- Official
- Best RDNA 3 consumer VRAM. Install the gfx110x family package, not gfx1201.
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 7900 XTX.
HSA_OVERRIDE: Not needed when the build lists gfx1100.
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.
| Model | Verdict |
|---|---|
| Qwen3.6-35B on RX 7900 XTX | Fits with RAM offload |
| Qwen 3.8 Flash on RX 7900 XTX | Fits with RAM offload |
| gpt-oss 20B on RX 7900 XTX | Fits fully on GPU |
| Gemma 3 27B on RX 7900 XTX | Needs 2 GPUs |
| Llama 3.3 70B on RX 7900 XTX | Fits with RAM offload |
| GLM 5.3 Flash on RX 7900 XTX | Fits with RAM offload |
| Qwen3.6 27B on RX 7900 XTX | Needs 2 GPUs |
| Qwen3.8 27B on RX 7900 XTX | Needs 2 GPUs |
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.
| Quant | Kind | Weights | 4K total | 32K total | Speed |
|---|---|---|---|---|---|
| Q6_K | Estimate | 26.7 GB | 27.7 GB Does not fit this GPU | 28.2 GB Does not fit this GPU | not measured |
| Q5_K_M | Estimate | 24.8 GB | 25.7 GB Does not fit this GPU | 26.2 GB Does not fit this GPU | not measured |
| Q4_K_M | Estimate | 19.8 GB | 20.6 GB Fits in VRAM (estimate) | 21.2 GB Fits in VRAM (estimate) | not measured |
| UD-Q3_K_XL | Q3 estimate | 15.6 GB | 16.4 GB Fits in VRAM (estimate) | 17.0 GB Fits in VRAM (estimate) | not measured |
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.
Minimum system RAM needed
32 GB kit
Estimate · 24.7 GiB raw · 32K context
RAM needed at full context
32 GB kit
Estimate · 25.6 GiB raw · 256K full context
Estimate. Offloaded weights + KV in RAM + runtime + OS/desktop + headroom, rounded up to a 32 GB DIMM kit.
Breakdown
- Offloaded weights ·
- 0 GiB
- Separable embed in RAM ·
- 0 GiB
- KV in RAM at selected ·
- 0 GiB
- KV in RAM at full context ·
- 0.82 GiB
- Runtime / backend ·
- 0.71 GiB
- OS / desktop baseline ·
- 8.00 GiB
- Headroom ·
- 16.0 GiB
llama.cpp-first stack
-
Step 1
llama.cpp first
Vulkan is the consumer default on this site. HIP when rocminfo lists gfx1100. Official on the cited ROCm 10.1 matrix — not Vulkan-only. Ollama and vLLM are not the house path for this card.
-
Step 2
gfx1100 family package
gfx1100 needs the gfx110x ROCm family package, same pin as the 7900 XT and 7900 GRE. Do not mix a gfx1201 (R9700 / 9070 XT) or gfx1200 (9060 XT) install. Re-check the cited matrix before you install.
-
Step 3
24 GB XTX, not the 20 GB XT
This sheet sizes the 24 GB consumer 7900 XTX. AMD product page: 24 GB GDDR6, RDNA 3, 355 W typical board power. Size Qwen3.6-35B-A3B on the calculator before you download. The 20 GB 7900 XT is a different listing at /gpus/rx-7900-xt. The R9700 remains the measured 32 GB north star.
-
Step 4
Setup, then Stack Lab doctor
First-run setup is Ubuntu. Open Stack Lab doctor for the gfx110x install family. House daily and Flash profiles are R9700 / local desktop — they do not apply to this 24 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 7900 XTX against the other published sheets:
Also: PRO W6800 · PRO W7700 · PRO W7800 · RX 6700 XT · RX 6800 XT · RX 6950 XT · RX 7600 · RX 7600 XT · RX 7700 XT · RX 7800 XT · RX 7900 GRE · RX 9060 XT · RX 9070 · RX 9070 GRE · Strix Halo
Check price · no live or invented prices
AMD Radeon RX 7900 XTX
- Amazon: check price
- Newegg: check price
- B&H Photo: check price
- Micro Center: check price
- AMD Store: check price
Return terms vary by seller and item. Newegg's Hassle-Free page covers only Sold-and-Shipped-by-Newegg listings; marketplace items use the seller's policy. See the listing's Warranty & Returns tab.
As an Amazon Associate I earn from qualifying purchases. Some Newegg links use Rakuten Advertising and some B&H links use B&H’s affiliate program when those IDs are configured. Micro Center and AMD Store links are plain “also available at” links — no tracking. Buttons say “Check price” and never invent or live-quote a price. Full disclosure.
Configurations we have
No first-party amdai-bench/run@1 card exists for this SKU. llama.cpp first. Empty cells stay empty. Fit numbers on this page are calculator estimates. Shopper RAM lines stay Minimum system RAM needed and RAM needed at full context — labeled estimate until measured.
No tested recipe yet — contribute. This card stays listed so the gap is visible.