AMD-Pro-BenchCommunity

13,812 benchmarks in 32 GPU combinations documented

DeepSeek-R1-Distill-Qwen-14B on R9700

22 results · 4 sources · 22 measurements

Explore all results

Grouped by reported model identity. Exact weights, quantizations and software can differ. How results are reviewed

Documented results

22 selected tests
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BQ4_K_MModel ref. ↗Token speed
136.54 tok/sInput + output · mean · per request
——1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux; kernel 6.17.5-v8-16k+
Engine
llama.cpp
Backend
Vulkan
Harness
Not reported
Prompt / output
4096 / 128 tokens
Context
Not reported
Concurrency
Not reported
Date
2025-11-24
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BBF16Model ref. ↗Token speed
41.5 tok/sThroughput · per request
——4 × R9700Tensor parallel · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (distribution not reported)
Engine
vLLM
Backend
ROCm 7.2.2 container / 6.4.3 host
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
1
Date
2026-05-22
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BFP8 dynamicModel ref. ↗Token speed
4,087.75 tok/sTotal throughput · mean · aggregate
——2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04.3 LTS
Engine
vLLM
Backend
ROCm 7.0.2
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2025-10-27
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BFP8-dynamicModel ref. ↗Relative performance
1.48 x vs RTX 4500 BlackwellRelative performance per dollar · Whole system
——1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04.3 LTS
Engine
Not reported
Backend
ROCm 6.4.2
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
Not reported
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BQ4_K_MModel ref. ↗Token speed—
508.82 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux; kernel 6.17.5-v8-16k+
Engine
llama.cpp
Backend
Vulkan
Harness
Not reported
Prompt / output
512 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2025-11-24
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BBF16Model ref. ↗Token speed——
42 tok/sGeneration · per request
4 × R9700Tensor parallel · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (distribution not reported)
Engine
vLLM
Backend
ROCm 7.2.2 container / 6.4.3 host
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
1
Date
2026-05-22
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BFP8 dynamicModel ref. ↗Token speed
464.79 tok/sThroughput · mean · aggregate
——2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04.3 LTS
Engine
vLLM
Backend
ROCm 7.0.2
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2025-10-27
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BQ4_K_MModel ref. ↗Token speed—
188.19 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux; kernel 6.17.5-v8-16k+
Engine
llama.cpp
Backend
Vulkan
Harness
Not reported
Prompt / output
4096 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2025-11-24
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BBF16Model ref. ↗Token speed
29.2 tok/sThroughput · per request
——2 × R9700Tensor parallel · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (distribution not reported)
Engine
vLLM
Backend
ROCm 7.2.2 container / 6.4.3 host
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
1
Date
2026-05-22
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BFP8 dynamicModel ref. ↗Latency
3,265.19 msLatency · Unknown
——2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04.3 LTS
Engine
vLLM
Backend
ROCm 7.0.2
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2025-10-27
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BQ4_K_MModel ref. ↗Token speed——
7.98 tok/sGeneration · mean · per request
1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux; kernel 6.17.5-v8-16k+
Engine
llama.cpp
Backend
Vulkan
Harness
Not reported
Prompt / output
? / 128 tokens
Context
Not reported
Concurrency
Not reported
Date
2025-11-24
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BBF16Model ref. ↗Token speed——
29.4 tok/sGeneration · per request
2 × R9700Tensor parallel · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (distribution not reported)
Engine
vLLM
Backend
ROCm 7.2.2 container / 6.4.3 host
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
1
Date
2026-05-22
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BFP8 dynamicModel ref. ↗Latency
3,267.94 msLatency · Unknown
——2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04.3 LTS
Engine
vLLM
Backend
ROCm 7.0.2
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2025-10-27
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BQ4_K_MModel ref. ↗Token speed
555.41 tok/sInput + output · mean · per request
——1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux; kernel 6.17.0-6-generic
Engine
llama.cpp
Backend
Vulkan
Harness
Not reported
Prompt / output
4096 / 128 tokens
Context
Not reported
Concurrency
Not reported
Date
2025-11-25
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BBF16Model ref. ↗Latency1 concurrent request
92 msTime to first token · Per request
——4 × R9700Tensor parallel · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (distribution not reported)
Engine
vLLM
Backend
ROCm 7.2.2 container / 6.4.3 host
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
1
Date
2026-05-22
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BFP8 dynamicModel ref. ↗Latency
3,269.52 msLatency · Unknown
——2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Ubuntu 24.04.3 LTS
Engine
vLLM
Backend
ROCm 7.0.2
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2025-10-27
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BQ4_K_MModel ref. ↗Token speed—
960.73 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux; kernel 6.17.0-6-generic
Engine
llama.cpp
Backend
Vulkan
Harness
Not reported
Prompt / output
512 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2025-11-25
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BBF16Model ref. ↗Latency1 concurrent request
116 msTime to first token · Per request
——2 × R9700Tensor parallel · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux (distribution not reported)
Engine
vLLM
Backend
ROCm 7.2.2 container / 6.4.3 host
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
1
Date
2026-05-22
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BQ4_K_MModel ref. ↗Token speed—
846.42 tok/sPrefill · mean · per request
—1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux; kernel 6.17.0-6-generic
Engine
llama.cpp
Backend
Vulkan
Harness
Not reported
Prompt / output
4096 / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2025-11-25
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BQ4_K_MModel ref. ↗Token speed——
53.72 tok/sGeneration · mean · per request
1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux; kernel 6.17.0-6-generic
Engine
llama.cpp
Backend
Vulkan
Harness
Not reported
Prompt / output
? / 128 tokens
Context
Not reported
Concurrency
Not reported
Date
2025-11-25
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BQ4_K_MModel ref. ↗Power & energy
279.7 WPower draw · Unknown
——1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux; kernel 6.17.5-v8-16k+
Engine
llama.cpp
Backend
Vulkan
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2025-11-24
Full record →
View
ReportGeneric LLM		DeepSeek-R1-Distill-Qwen-14BQ4_K_MModel ref. ↗Power & energy
330.8 WPower draw · Unknown
——1 × R9700Single GPU · 32 GB VRAM/GPU
Configuration
Memory
32 GB VRAM/GPU
OS
Linux; kernel 6.17.0-6-generic
Engine
llama.cpp
Backend
Vulkan
Harness
Not reported
Prompt / output
? / ? tokens
Context
Not reported
Concurrency
Not reported
Date
2025-11-25
Full record →
Quantizations and software

Quantizations: BF16, FP8 dynamic, FP8-dynamic, Q4_K_M
Engines: llama.cpp, vLLM

Explore all 22 results →

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

GPU benchmark pages: R9700