llamaperf

AMD Radeon Pro W7800 48GB

AMD · 48GB · 2 reports

Is this your card?

On the AMD Radeon Pro W7800 48GB, Qwen3.8 125B · 6B active at 3-bit, the model most run on it, generates a median of 90.0 tokens per second from one plain run (community reports, as of 22 Nov 2026).

As of 22 Nov 2026, the models most run on the AMD Radeon Pro W7800 48GB, each one size at one quant level, with the median generation speed of its plain runs (one device, one request, no speculative decoding):

Bars are medians on one scale, 0 to 90.0 tokens/s. Press ▶ to watch text arrive at a row's speed.

Engines people use on it: llama.cpp 2 (reports)

Run models on your AMD Radeon Pro W7800 48GB? Add your numbers.

Your coding agent can run a speed test on your machine and send it here with a free account. Or paste a result you've already posted.

Reported performance on the AMD Radeon Pro W7800 48GB

These reports mix GPU counts and memory setups, so a model listed here may have needed extra cards or CPU offloading. The calculator estimates which models fit in 48 GB of VRAM. Prompt processing is how fast the input is read, not how long you wait for the first word. How to measure time to first token.

2 reports on this card so far, so treat the figures as early. Add yours.

Speeds are as each source reported them. GPU count, offloading and concurrent requests change them, and prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing two reports.

AMD hardware
generation:
154.1 tokens/s
quant:
UD-Q4_K_S (GGUF)

User reports Qwen3.6-35B-A3B at 154.12 t/s with MTP on 2x AMD Radeon PRO W7800 48GB. Setup is llama.cpp (Lemonade stack) with UD-Q4_K_S GGUF and tensor-split across both cards; stock decode without MTP is 79.86 t/s, and MTP drops to 146.7 t/s at 8k and 132.6 t/s at 32k. Part of a registry PR adding 40 recipes for the W7800 48GB; other models in the table include Qwen3-Coder 30B-A3B, Ornith 1.5 35B-A3B, Gemma 4 26B-A4B-it, Qwen3.8 Uncensored and Qwen3.6-27B.

Oct 8, 2026
Tone: mixedAMD hardware
generation:
90.0 tokens/s
quant:
IQ3_XXS (GGUF)
kv:
Q8
coding

User reports Qwen 3.8 Flash-Next at about 90 t/s on a Radeon Pro W7800 48GB with 64GB DDR5 system RAM. Setup is llama.cpp with an IQ3_XXS GGUF quant, 128k context and Q8 KV cache, run with default settings. The user is satisfied with the speed but the model fell into repetition loops after 3-4 minutes of reasoning on a 27KB JavaScript audit task, repeating the same steps dozens of times; they interrupted it twice and ask whether a reasoning budget setting is the cause.

Oct 5, 2026

Get a weekly email of new AMD Radeon Pro W7800 48GB reports and newly released models that fit it.

Email me new reports

Reported configurations

Individual observations from this page, not expected speeds or a ranking. Select a model to open its report, with the source and offloading conditions. Reported context may be a limit rather than actual input length.

Model / hardwareQuant / engineReported contextGeneration
Qwen3.6 35B (3B active)
2× AMD Radeon Pro W7800 48GB
UD-Q4_K_S
llama.cpp
Not reported154.1 tokens/s
Qwen3.8 125B (6B active) Flash-Next
AMD Radeon Pro W7800 48GB
IQ3_XXS
llama.cpp
131,07290.0 tokens/s

Frequently asked

How fast is the AMD Radeon Pro W7800 48GB for local LLMs?

On the AMD Radeon Pro W7800 48GB, Qwen3.8 125B · 6B active at 3-bit, the model most run on it, generates a median of 90.0 tokens per second from one plain run (community reports, as of 22 Nov 2026).