Models
Loading community benchmarks…
Loading community benchmarks…
Submitted benchmarks for Gemma 4 E4B IT. Browse individual runs and their measurement settings, or open the report JSON for full benchmark details.
Peak throughput is the highest reported value and may come from different runs. Compare model, quantisation, backend, and token counts before drawing conclusions. Model verification identifies published artifact bytes; community benchmark execution is not remotely attested.
| Date |
|---|
| Report |
|---|
basecompute/gemma-4-E4B-it BaseRTQ4· default-q4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Pro Metal | 45.9 tok/s TG128 | 565 tok/s PP512 | 3,580.4 MiB | lukas | View Benchmark | |
basecompute/gemma-4-E4B-it BaseRTQ4· default-q4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M5 Pro Metal | 82.6 tok/s TG128 | 4,656 tok/s PP512 | 3,339.4 MiB | arki05 | View Benchmark | |
basecompute/gemma-4-E4B-it BaseRTQ8· default-q8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M5 Pro Metal | 51.3 tok/s TG128 | 4,490 tok/s PP512 | 5,538.8 MiB | arki05 | View Benchmark | |
Gemma-4-E4B-It llama.cppQ4_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M5 Pro BLAS + Metal | 72.1 tok/s TG128 | 2,263 tok/s PP512 | 5,321.4 MiB | arki05 | View Benchmark | |
Gemma-4-E4B-It llama.cppQ4_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M5 Pro BLAS + Metal | 69.4 tok/s TG128 | 2,235 tok/s PP512 | 5,463.1 MiB | arki05 | View Benchmark | |
Gemma-4-E4B-It llama.cppQ8_0 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M5 Pro BLAS + Metal | 47.9 tok/s TG128 | 2,346 tok/s PP512 | 8,387.1 MiB | arki05 | View Benchmark | |
basecompute/gemma-4-E4B-it BaseRTQ4· default-q4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Metal | 15.7 tok/s TG128 | 205 tok/s PP512 | 3,324.3 MiB | pyopyo | View Benchmark | |
basecompute/gemma-4-E4B-it BaseRTQ4· default-q4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Metal | 15.8 tok/s TG128 | 259 tok/s PP512 | 3,383.2 MiB | pyopyo | View Benchmark | |
basecompute/gemma-4-E4B-it BaseRTQ4· default-q4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M5 Pro Metal | 81.9 tok/s TG128 | 4,636 tok/s PP512 | 3,339.0 MiB | arki05 | View Benchmark | |
basecompute/gemma-4-E4B-it BaseRTQ8· default-q8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M5 Pro Metal | 51.0 tok/s TG128 | 4,462 tok/s PP512 | 5,537.8 MiB | arki05 | View Benchmark | |
Gemma-4-E4B-It llama.cppQ4_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | AMD Radeon RX 7900 XT ROCm | 111.0 tok/s TG128 | 4,443 tok/s PP512 | 6,586.0 MiB | arki05 | View Benchmark | |
Gemma-4-E4B-It llama.cppQ4_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | AMD Radeon RX 7900 XT ROCm | 109.3 tok/s TG128 | 4,369 tok/s PP512 | 6,783.5 MiB | arki05 | View Benchmark | |
Gemma-4-E4B-It llama.cppQ8_0 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | AMD Radeon RX 7900 XT ROCm | 84.3 tok/s TG128 | 4,564 tok/s PP512 | 9,708.0 MiB | arki05 | View Benchmark | |
Gemma-4-E4B-It llama.cppQ4_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | AMD Radeon RX 7900 XT (RADV NAVI31) Vulkan | 126.6 tok/s TG128 | 4,142 tok/s PP512 | 4,934.6 MiB | arki05 | View Benchmark | |
Gemma-4-E4B-It llama.cppQ4_K_M The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | AMD Radeon RX 7900 XT (RADV NAVI31) Vulkan | 122.8 tok/s TG128 | 4,161 tok/s PP512 | 5,076.7 MiB | arki05 | View Benchmark | |
Gemma-4-E4B-It llama.cppQ8_0 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | AMD Radeon RX 7900 XT (RADV NAVI31) Vulkan | 95.6 tok/s TG128 | 4,214 tok/s PP512 | 8,001.2 MiB | arki05 | View Benchmark | |
basecompute/gemma-4-E4B-it BaseRTQ4· default-q4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M5 Max Metal | 121.1 tok/s TG128 | 8,156 tok/s PP512 | 3,383.0 MiB | lukas | View Benchmark | |
gemma-4-E4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | NVIDIA GB10 CUDA | 71.3 tok/s TG128 @ 1 ctx | 3,674 tok/s PP512 | 4,738.5 MiB | basecompute | View Benchmark | |
gemma-4-E4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max Metal | 109.3 tok/s TG128 @ 1 ctx | 2,552 tok/s PP512 | 3,326.8 MiB | basecompute | View Benchmark | |
gemma-4-E4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Max Metal | 77.4 tok/s TG128 @ 1 ctx | 2,481 tok/s PP512 | 5,526.5 MiB | basecompute | View Benchmark | |
gemma-4-E4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro Metal | 44.5 tok/s TG128 @ 1 ctx | 1,081 tok/s PP512 | 5,525.7 MiB | basecompute | View Benchmark | |
gemma-4-E4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max Metal | 52.0 tok/s TG128 @ 1 ctx | 1,368 tok/s PP512 | 5,526.1 MiB | basecompute | View Benchmark | |
gemma-4-E4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M1 Max Metal | 75.9 tok/s TG128 @ 1 ctx | 1,394 tok/s PP512 | 3,326.7 MiB | basecompute | View Benchmark | |
gemma-4-E4B-it-Q4 BaseRTQ4 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M4 Pro Metal | 69.1 tok/s TG128 @ 1 ctx | 1,094 tok/s PP512 | 3,326.1 MiB | basecompute | View Benchmark | |
gemma-4-E4B-it-Q8 BaseRTQ8 The report's model SHA-256 matches a file published on Hugging Face, so the exact model bytes are known. This does not attest benchmark execution. | Apple M3 Ultra Metal | 75.4 tok/s TG128 @ 1 ctx | 3,499 tok/s PP512 | 5,523.3 MiB | basecompute | View Benchmark |