AMD RX 7900 GRE 16GB

AMD · 16GB · 3 reports

Engines people use on it: llama.cpp 3 (reports)

See reported performance Estimate what fits

How to compare these reports →Filter reports by setup →Best local LLMs for 16 GB of VRAM →

Run models on your AMD RX 7900 GRE 16GB? 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.

Benchmark with your agent Paste a result

Reported performance on the AMD RX 7900 GRE 16GB

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 16 GB of VRAM.

Date ↓Date ↑Token speed ↓Token speed ↑Prefill ↓Prefill ↑Context ↓Context ↑Ranked

Qwen3 8B

AMD RX 7900 GRE 16GB · llama.cpp

generation:: 133.0 tokens/s
quant:: Q8_0 (GGUF)

Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.

User benchmarks Qwen3-8B Q8_0 with DSpark speculative decoding in llama.cpp on an RX 7900 GRE 16GB, reaching 133 t/s on ROCm versus 59 t/s without speculation, and 115 t/s versus 62 t/s on Vulkan. Setup is llama.cpp with Q8_0 weights, greedy decoding, one user and 32 prompts per setting. DFlash gave 1.5-1.9x, a 0.6B draft model about 1.3x, and n-gram lookup did nothing. The best number of guessed tokens is 3 on Vulkan and 7 on ROCm, and prompt processing is about 8% slower with DSpark loaded. Only 5-6 of 16 answers matched normal decoding word for word.

Gemma 4 26B (4B active) Uncensored-HauhauCS-Balanced

2× AMD RX 7900 GRE 16GB · llama.cpp

generation:: 51.9 tokens/s
prompt processing (prefill):: 322.0 tokens/s
quant:: Q4_K_M (GGUF)

Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.

User reports a 36% improvement in generation speed with a dual GPU setup of an RX 7900 GRE 16GB and an RX 480 8GB. The user tested medgemma-27b-it-UD-Q6_K_XL, Qwen3.8-27B-Q6_K, Qwen3.8-27B-OBLITERATED-Q5_K_M, and Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-Q4_K_M, with and without Flash Attention.

Qwen3.8 27B

AMD RX 7900 GRE 16GB · llama.cpp

generation:: 11.8 tokens/s
prompt processing (prefill):: 87.5 tokens/s
quant:: Q4_K_M (GGUF)

User benchmarks Qwen3.8-27B, identified as Qwen3.5 in llama.cpp, using llama.cpp RPC across multiple GPUs. Setup is an RX 7900 GRE 16GB as the main host, with RPC combinations including RX 7900 GRE + GTX 1080Ti and GTX 1080Ti + two P102-100, in Q4_K_M and Q6_K quants. Results vary by config; the best generation is about 12.53 t/s with Q6_K on RX 7900 GRE + GTX 1080Ti.

Get a weekly email of new AMD RX 7900 GRE 16GB 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 / hardware	Quant / engine	Reported context	Generation
Qwen3 8B AMD RX 7900 GRE 16GB	Q8_0 llama.cpp	Not reported	133.0 tokens/s
Gemma 4 26B (4B active) Uncensored-HauhauCS-Balanced 2× AMD RX 7900 GRE 16GB	Q4_K_M llama.cpp	Not reported	51.9 tokens/s
Qwen3.8 27B AMD RX 7900 GRE 16GB	Q4_K_M llama.cpp	Not reported	11.8 tokens/s