Models

Loading community benchmarks…

← All models

Community benchmarks

Qwen3 4B Instruct 2507

Submitted benchmarks for Qwen3 4B Instruct 2507. Browse individual runs and their measurement settings, or open the report JSON for full benchmark details.

Compare chips Compare runtimes Add your benchmark

Submitted runs: 23
Chips tested: 8
Contributors: 2

Model identity

Grouped as Qwen/Qwen3-4B-Instruct-2507. 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.. Artifact verification confirms published model bytes, not that a community-submitted benchmark was honestly executed. Hover or tap a label for what it means.

This model group collects runs reported as basecompute/Qwen3-4B-Instruct-2507, Qwen3-4B-Instruct-2507, Qwen3-4B-Instruct-2507-Q4, Qwen3-4B-Instruct-2507-Q8. Individual results keep the package name and format they were submitted with.

View on Hugging Face ↗

Published files benchmarked

basecompute/Qwen3-4B-Instruct-2507/Qwen3-4B-Instruct-2507-Q4.base (opens in a new tab)BaseRTQ4· 7 runs
basecompute/Qwen3-4B-Instruct-2507/Qwen3-4B-Instruct-2507-Q8.base (opens in a new tab)BaseRTQ8· 7 runs
unsloth/Qwen3-4B-Instruct-2507-GGUF/Qwen3-4B-Instruct-2507-Q4_K_M.gguf (opens in a new tab)llama.cppQ4_K_M· 3 runs

Benchmark results

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.

Individual runs for Qwen3 4B Instruct 2507. Throughput is in tokens per second; dates use your browser timezone. Hover a date for the exact local time.
Model / runtime / format	Chip / backend	Decode	Prefill	Peak process memory	Contributor

basecompute/Qwen3-4B-Instruct-2507 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	89.4 tok/s TG128	3,359 tok/s PP512	3,909.1 MiB	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-4B-Instruct-2507 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	64.3 tok/s TG128	3,398 tok/s PP512	6,047.5 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507 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	94.4 tok/s TG128	2,568 tok/s PP512	4,860.1 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507 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	92.6 tok/s TG128	2,566 tok/s PP512	4,902.8 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507 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	60.8 tok/s TG128	2,686 tok/s PP512	6,558.2 MiB	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-4B-Instruct-2507 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	90.4 tok/s TG128	3,331 tok/s PP512	3,908.9 MiB	arki05	11 Sep 2026	View Benchmark
basecompute/Qwen3-4B-Instruct-2507 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	62.8 tok/s TG128	3,405 tok/s PP512	6,047.2 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507 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	147.8 tok/s TG128	5,364 tok/s PP512	4,211.3 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507 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	147.1 tok/s TG128	5,337 tok/s PP512	4,254.3 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507 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	110.8 tok/s TG128	5,581 tok/s PP512	5,908.0 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507 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	185.1 tok/s TG128	4,783 tok/s PP512	424.9 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507 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	180.3 tok/s TG128	4,793 tok/s PP512	425.5 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507 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	134.3 tok/s TG128	4,824 tok/s PP512	4,200.9 MiB	arki05	11 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507-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	73.7 tok/s TG128 @ 1 ctx	11,246 tok/s PP512	3,379.4 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507-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.	NVIDIA GB10 CUDA	54.8 tok/s TG128 @ 1 ctx	10,970 tok/s PP512	4,520.0 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507-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	121.9 tok/s TG128 @ 1 ctx	1,711 tok/s PP512	3,897.2 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507-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	104.3 tok/s TG128 @ 1 ctx	1,723 tok/s PP512	6,035.8 MiB	basecompute	19 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507-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	72.1 tok/s TG128 @ 1 ctx	925 tok/s PP512	6,038.4 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507-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	91.3 tok/s TG128 @ 1 ctx	922 tok/s PP512	3,898.2 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507-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	56.2 tok/s TG128 @ 1 ctx	731 tok/s PP512	6,037.3 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507-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	118.3 tok/s TG128 @ 1 ctx	2,557 tok/s PP512	6,032.5 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507-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 M3 Ultra Metal	153.7 tok/s TG128 @ 1 ctx	2,529 tok/s PP512	3,894.0 MiB	basecompute	20 Sep 2026	View Benchmark
Qwen3-4B-Instruct-2507-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	77.9 tok/s TG128 @ 1 ctx	727 tok/s PP512	3,898.9 MiB	basecompute	20 Sep 2026	View Benchmark