AMD-Pro-BenchCommunity

13,812 benchmarks in 32 GPU combinations documented

OmniDocBench results on AMD GPUs

45 results · 4 sources · 45 measurements

Scores from different versions, task subsets, harnesses and scoring rules are not directly comparable. How results are reviewed

Documented results

24 selected tests
View
Report
Generic LLM
MinerU2.5-Pro-2605-1.2BBF16Weights ↗OmniDocBenchFull1651 pages · v1.68K configured context
95.56 %Overall · n = 100 · Official page-level aggregates
——1 × W7900Single GPU · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Linux (kernel6.8.0-79-generic)
Engine
vLLM
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
8192
Concurrency
Not reported
Date
2026-07-21
Full record →
View
Report
Generic LLM
HunyuanOCRBF16Weights ↗OmniDocBenchFull1651 pages · v1.6
94.05 %Overall · n = 100 · Official page-level aggregates
——3 × W7900Independent replicas · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Linux
Engine
Transformers
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-07-31
Full record →
View
Report
Generic LLM
HunyuanOCRBF16Weights ↗OmniDocBenchFull1651 pages · v1.61 concurrent request
93.64 %Overall · n = 100 · Official page-level aggregates
——GPU count unknownUnknown · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Linux
Engine
vLLM
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
1
Date
2026-07-25
Full record →
View
Report
Generic LLM
MinerU2.5-Pro-2605-1.2BQuant not reportedModel ref. ↗OmniDocBenchFull1651 pages · v1.6
0.04 edit distanceText edit distance · quick_match_cdm · Lower is better
——1 × Ryzen AI Max+ 395Single GPU · Unified memory · 128 GB RAM
Configuration
Memory
Unified memory · 128 GB RAM
OS
Windows 11
Engine
llama.cpp
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-08-01
Full record →
View
Report
Generic LLM
MinerU2.5-Pro-2605-1.2BBF16Weights ↗OmniDocBenchFull1651 pages · v1.68K configured context
0.04 edit distanceText edit distance · Official page-level aggregates · Lower is better
——1 × W7900Single GPU · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Linux (kernel6.8.0-79-generic)
Engine
vLLM
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
8192
Concurrency
Not reported
Date
2026-07-21
Full record →
View
Report
Generic LLM
HunyuanOCRBF16Weights ↗OmniDocBenchFull1651 pages · v1.6
0.04 edit distanceText edit distance · Official page-level aggregates · Lower is better
——3 × W7900Independent replicas · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Linux
Engine
Transformers
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-07-31
Full record →
View
Report
Generic LLM
HunyuanOCRBF16Weights ↗OmniDocBenchFull1651 pages · v1.61 concurrent request
0.05 edit distanceText edit distance · Official page-level aggregates · Lower is better
——GPU count unknownUnknown · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Linux
Engine
vLLM
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
1
Date
2026-07-25
Full record →
View
Report
Generic LLM
MinerU2.5-Pro-2605-1.2BQuant not reportedModel ref. ↗OmniDocBenchFull1651 pages · v1.6
0.12 edit distanceReading-order edit distance · quick_match_cdm · Lower is better
——1 × Ryzen AI Max+ 395Single GPU · Unified memory · 128 GB RAM
Configuration
Memory
Unified memory · 128 GB RAM
OS
Windows 11
Engine
llama.cpp
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-08-01
Full record →
View
Report
Generic LLM
MinerU2.5-Pro-2605-1.2BBF16Weights ↗OmniDocBenchFull1651 pages · v1.68K configured context
93.54 %Table TEDS · n = 100 · Official page-level aggregates
——1 × W7900Single GPU · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Linux (kernel6.8.0-79-generic)
Engine
vLLM
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
8192
Concurrency
Not reported
Date
2026-07-21
Full record →
View
Report
Generic LLM
HunyuanOCRBF16Weights ↗OmniDocBenchFull1651 pages · v1.6
93.33 %Table TEDS · n = 100 · Official page-level aggregates
——3 × W7900Independent replicas · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Linux
Engine
Transformers
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-07-31
Full record →
View
Report
Generic LLM
HunyuanOCRBF16Weights ↗OmniDocBenchFull1651 pages · v1.61 concurrent request
92.97 %Table TEDS · n = 100 · Official page-level aggregates
——GPU count unknownUnknown · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Linux
Engine
vLLM
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
1
Date
2026-07-25
Full record →
View
Report
Generic LLM
MinerU2.5-Pro-2605-1.2BQuant not reportedModel ref. ↗OmniDocBenchFull1651 pages · v1.6
93.11 %Table TEDS (pooled) · n = 1 · quick_match_cdm
——1 × Ryzen AI Max+ 395Single GPU · Unified memory · 128 GB RAM
Configuration
Memory
Unified memory · 128 GB RAM
OS
Windows 11
Engine
llama.cpp
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-08-01
Full record →
View
Report
Generic LLM
MinerU2.5-Pro-2605-1.2BBF16Weights ↗OmniDocBenchFull1651 pages · v1.68K configured context
96.73 %Formula CDM · n = 100 · Official page-level aggregates
——1 × W7900Single GPU · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Linux (kernel6.8.0-79-generic)
Engine
vLLM
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
8192
Concurrency
Not reported
Date
2026-07-21
Full record →
View
Report
Generic LLM
HunyuanOCRBF16Weights ↗OmniDocBenchFull1651 pages · v1.6
92.6 %Formula CDM · n = 100 · Official page-level aggregates
——3 × W7900Independent replicas · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Linux
Engine
Transformers
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-07-31
Full record →
View
Report
Generic LLM
HunyuanOCRBF16Weights ↗OmniDocBenchFull1651 pages · v1.61 concurrent request
92.46 %Formula CDM · n = 100 · Official page-level aggregates
——GPU count unknownUnknown · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Linux
Engine
vLLM
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
1
Date
2026-07-25
Full record →
View
Report
Generic LLM
MinerU2.5-Pro-2605-1.2BQuant not reportedModel ref. ↗OmniDocBenchFull1651 pages · v1.6
97.01 %Formula CDM · n = 1 · quick_match_cdm
——1 × Ryzen AI Max+ 395Single GPU · Unified memory · 128 GB RAM
Configuration
Memory
Unified memory · 128 GB RAM
OS
Windows 11
Engine
llama.cpp
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-08-01
Full record →
View
Report
Generic LLM
MinerU2.5-Pro-2605-1.2BBF16Weights ↗OmniDocBenchFull1651 pages · v1.68K configured context
0.12 edit distanceReading-order edit distance · Official page-level aggregates · Lower is better
——1 × W7900Single GPU · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Linux (kernel6.8.0-79-generic)
Engine
vLLM
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
8192
Concurrency
Not reported
Date
2026-07-21
Full record →
View
Report
Generic LLM
HunyuanOCRBF16Weights ↗OmniDocBenchFull1651 pages · v1.6
0.13 edit distanceReading-order edit distance · Official page-level aggregates · Lower is better
——3 × W7900Independent replicas · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Linux
Engine
Transformers
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-07-31
Full record →
View
Report
Generic LLM
HunyuanOCRBF16Weights ↗OmniDocBenchFull1651 pages · v1.61 concurrent request
0.14 edit distanceReading-order edit distance · Official page-level aggregates · Lower is better
——GPU count unknownUnknown · 48 GB VRAM/GPU
Configuration
Memory
48 GB VRAM/GPU
OS
Linux
Engine
vLLM
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
1
Date
2026-07-25
Full record →
View
Report
Generic LLM
MinerU2.5-Pro-2605-1.2BQuant not reportedModel ref. ↗OmniDocBenchFull1651 pages · v1.6
95.46 %Overall · n = 100 · quick_match_cdm
——1 × Ryzen AI Max+ 395Single GPU · Unified memory · 128 GB RAM
Configuration
Memory
Unified memory · 128 GB RAM
OS
Windows 11
Engine
llama.cpp
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-08-01
Full record →
View
Report
Generic LLM
PaddleOCR-VL-1.6Quant not reportedModel ref. ↗OmniDocBenchFull1651 pages · v1.6
0.04 edit distanceText edit distance · text_ro_page_avg_teds_pooled_cdm_pooled · Lower is better
——1 × Ryzen AI Max+ 395Single GPU · Unified memory · 128 GB RAM
Configuration
Memory
Unified memory · 128 GB RAM
OS
Windows 11
Engine
llama.cpp
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-08-06
Full record →
View
Report
Generic LLM
PaddleOCR-VL-1.6Quant not reportedModel ref. ↗OmniDocBenchFull1651 pages · v1.6
0.13 edit distanceReading-order edit distance · text_ro_page_avg_teds_pooled_cdm_pooled · Lower is better
——1 × Ryzen AI Max+ 395Single GPU · Unified memory · 128 GB RAM
Configuration
Memory
Unified memory · 128 GB RAM
OS
Windows 11
Engine
llama.cpp
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-08-06
Full record →
View
Report
Generic LLM
PaddleOCR-VL-1.6Quant not reportedModel ref. ↗OmniDocBenchFull1651 pages · v1.6
92.98 %Table TEDS (pooled) · n = 1 · text_ro_page_avg_teds_pooled_cdm_pooled
——1 × Ryzen AI Max+ 395Single GPU · Unified memory · 128 GB RAM
Configuration
Memory
Unified memory · 128 GB RAM
OS
Windows 11
Engine
llama.cpp
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-08-06
Full record →
View
Report
Generic LLM
PaddleOCR-VL-1.6Quant not reportedModel ref. ↗OmniDocBenchFull1651 pages · v1.6
94.1 %Table TEDS (page average) · n = 1 · text_ro_page_avg_teds_pooled_cdm_pooled
——1 × Ryzen AI Max+ 395Single GPU · Unified memory · 128 GB RAM
Configuration
Memory
Unified memory · 128 GB RAM
OS
Windows 11
Engine
llama.cpp
Backend
ROCm / HIP
Harness
OmniDocBench quick_match + CDM
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2026-08-06
Full record →
Versions and harnesses

Versions: Not reported
Harnesses: OmniDocBench quick_match + CDM

Explore all 45 results →

This is a selection across sources, not a ranking or a matched experiment. Reading benchmark reports

GPU benchmark pages: W7900 · Ryzen AI Max+ 395