GPUs & Macs › AMD Radeon RX 7700S

AMD Radeon RX 7700S: local LLM speed

1 measured result for the AMD Radeon RX 7700S.

Measured results

ModelGenerate
tok/s
Prompt
tok/s
QuantBackendTestSource
Llama 3.1 8B Instruct4.6289Q4_K_Mllamafile LocalScore avgLocalScore details

What fits on the AMD Radeon RX 7700S

Estimates for this chip are scaled from a measured run: Llama 3.1 8B Instruct Q4_K_M at 4.6 tok/s (llamafile, source). Fit assumes the whole model in GPU memory with ~8K context.

ModelBest quant that fitsFileExpected tok/s
gemma-4-12B-itIQ4_XS6.4 GB3.5 estimate
Qwen3.5-9BQ5_K_S6.4 GB3.5 estimate
Qwen3.5-4BQ8_04.5 GB5.0 estimate
MiMo-V2.6-Distill-Qwen-9BQ4_K_M5.8 GB3.8 estimate
gemma-4-E4B-itQ5_K_M5.5 GB4.1 estimate
Qwen3-4BQ8_04.3 GB5.2 estimate
gemma-3-1b-itQ8_01.1 GB18.7 estimate
gemma-4-E2B-itQ8_05.0 GB4.5 estimate
DeepSeek-R1-0528-Qwen3-8BQ5_K_M5.9 GB3.8 estimate
Llama-3.2-3B-InstructQ8_03.4 GB6.5 estimate
Phi-4-mini-instructQ8_04.1 GB5.5 estimate
gemma-3-4b-itQ8_04.1 GB5.4 estimate
Qwen3-14BUD-IQ3_XXS6.0 GB3.7 estimate
gemma-3-12b-itQ3_K_M6.0 GB3.7 estimate

Open in the picker

Similar hardware

AMD Radeon RX 5700 XT · AMD Radeon RX Vega 64 · AMD Radeon RX 6650 XT · AMD Radeon RX 7600 · AMD Radeon RX 6600 XT · AMD Radeon RX 6600 · AMD Radeon RX Vega 56 · AMD Radeon RX 580