GLM 5/5.1 · MI355X · Precision comparison
MI355X: FP4 vs FP8 precision comparison
How FP4 and FP8 precision affect GLM 5/5.1 inference on MI355X (AMD CDNA 4). Throughput, latency, and cost across LLM workloads. Use the chart controls below to switch sequences and metrics — same interactions as the main inference chart.
Near the low end of the 12–66 tok/s/user interactivity band, at 25 tok/s/user on GLM 5/5.1 (MI355X): FP4 runs 1,169 tok/s/chip at $0.36 per million tokens, FP8 runs 987 at $0.42. FP4 delivers 18% more tok/s/chip on the same chip, which makes it 16% cheaper per token. Precision changes affect both inference speed and model quality — consult the evaluation tab for accuracy benchmarks.
At 39 tok/s/user on GLM 5/5.1 (MI355X), FP4 delivers 525 tok/s/chip at $0.79 per million tokens; FP8 delivers 809 tok/s/chip at $0.51. FP8 delivers 54% more tok/s/chip on the same chip, which makes it 35% cheaper per token. Lower-precision quantization trades model accuracy for throughput — check the evaluation page for quality impact.
FP4 posts 255 tok/s/chip for $1.63 per million tokens at 53 tok/s/user on GLM 5/5.1 (MI355X); FP8 posts 447 tok/s/chip for $0.93. FP8 delivers 76% more tok/s/chip on the same chip, which makes it 43% cheaper per token. Quantization-level accuracy differences are tracked on the evaluation tab. (Numbers reflect the default 1k/1k selection for this URL — table and chart below update if you change sequence or model in the controls. Each side uses the best available serving configuration for that precision, which may include speculative decoding such as MTP where recipes exist — the same convention as the other comparison pages.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | FP41,169FP8987 | FP4525FP8809 | FP4255FP8447 |
| Cost ($/M tok) | FP4$0.36FP8$0.42 | FP4$0.79FP8$0.51 | FP4$1.63FP8$0.93 |
| tok/s/MW | FP4559,384FP8472,302 | FP4251,405FP8387,141 | FP4121,953FP8214,074 |
| Concurrency | FP4~94FP8~128 | FP4~27FP8~108 | FP4~10FP8~17 |
