Qwen2.5-7B-Instruct on R9700

18 results · 2 sources · 18 measurements

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

Documented results

18 selected tests


View ReportCustom evaluation	Qwen2.5-7B-InstructQ6_KModel ref. ↗	Unspecified evaluation512 configured context	7.552 PPLScore · Lower is better	—	—	2 × R9700Tensor parallel · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 LTS / Linux 7.0.0-28-generic Engine llama.cpp Backend ROCm / HIP Harness llama-perplexity Prompt / output ? / ? tokens Context 512 Concurrency Not reported Date 2026-08-05 Full record →
View ReportGeneric LLM	Qwen2.5-7B-InstructQ4_K_MModel ref. ↗	Token speed	—	2,964 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 Engine llama.cpp Backend HIP / ROCm 7.2.0 Harness Not reported Prompt / output 128 / ? tokens Context 8192 Concurrency Not reported Date Not reported Full record →
View ReportCustom evaluation	Qwen2.5-7B-InstructQ6_KModel ref. ↗	Unspecified evaluation512 configured context	7.552 PPLScore · Lower is better	—	—	2 × R9700Tensor parallel · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 LTS / Linux 7.0.0-28-generic Engine llama.cpp Backend ROCm / HIP Harness llama-perplexity Prompt / output ? / ? tokens Context 512 Concurrency Not reported Date 2026-08-05 Full record →
View ReportGeneric LLM	Qwen2.5-7B-InstructQ4_K_MModel ref. ↗	Token speed	—	3,781 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 Engine llama.cpp Backend HIP / ROCm 7.2.0 Harness Not reported Prompt / output 256 / ? tokens Context 8192 Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Qwen2.5-7B-InstructQ6_KModel ref. ↗	Token speed	—	2,869.17 tok/sPrefill · mean · per request	—	2 × R9700Tensor parallel · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 LTS / Linux 7.0.0-28-generic Engine llama.cpp Backend ROCm / HIP Harness llama-bench Prompt / output 512 / 0 tokens Context Not reported Concurrency 1 Date 2026-08-05 Full record →
View ReportGeneric LLM	Qwen2.5-7B-InstructQ4_K_MModel ref. ↗	Token speed	—	4,006 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 Engine llama.cpp Backend HIP / ROCm 7.2.0 Harness Not reported Prompt / output 512 / ? tokens Context 8192 Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Qwen2.5-7B-InstructQ6_KModel ref. ↗	Token speed	—	—	104.61 tok/sGeneration · mean · per request	2 × R9700Tensor parallel · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 LTS / Linux 7.0.0-28-generic Engine llama.cpp Backend ROCm / HIP Harness llama-bench Prompt / output 0 / 128 tokens Context Not reported Concurrency 1 Date 2026-08-05 Full record →
View ReportGeneric LLM	Qwen2.5-7B-InstructQ4_K_MModel ref. ↗	Token speed	—	—	103.7 tok/sGeneration · mean · per request	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 Engine llama.cpp Backend HIP / ROCm 7.2.0 Harness Not reported Prompt / output ? / 128 tokens Context 8192 Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Qwen2.5-7B-InstructQ6_KModel ref. ↗	Token speed	—	2,870.34 tok/sPrefill · mean · per request	—	2 × R9700Tensor parallel · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 LTS / Linux 7.0.0-28-generic Engine llama.cpp Backend ROCm / HIP Harness llama-bench Prompt / output 512 / 0 tokens Context Not reported Concurrency 1 Date 2026-08-05 Full record →
View ReportGeneric LLM	Qwen2.5-7B-InstructQ5_K_MModel ref. ↗	Token speed	—	2,798 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 Engine llama.cpp Backend HIP / ROCm 7.2.0 Harness Not reported Prompt / output 128 / ? tokens Context 8192 Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Qwen2.5-7B-InstructQ6_KModel ref. ↗	Token speed	—	—	117.66 tok/sGeneration · mean · per request	2 × R9700Tensor parallel · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 LTS / Linux 7.0.0-28-generic Engine llama.cpp Backend ROCm / HIP Harness llama-bench Prompt / output 0 / 128 tokens Context Not reported Concurrency 1 Date 2026-08-05 Full record →
View ReportGeneric LLM	Qwen2.5-7B-InstructQ5_K_MModel ref. ↗	Token speed	—	3,585 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 Engine llama.cpp Backend HIP / ROCm 7.2.0 Harness Not reported Prompt / output 256 / ? tokens Context 8192 Concurrency Not reported Date Not reported Full record →
View ReportGeneric LLM	Qwen2.5-7B-InstructQ5_K_MModel ref. ↗	Token speed	—	3,040 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 Engine llama.cpp Backend HIP / ROCm 7.2.0 Harness Not reported Prompt / output 512 / ? tokens Context 8192 Concurrency Not reported Date Not reported Full record →
View ReportGeneric LLM	Qwen2.5-7B-InstructQ5_K_MModel ref. ↗	Token speed	—	—	93.3 tok/sGeneration · mean · per request	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 Engine llama.cpp Backend HIP / ROCm 7.2.0 Harness Not reported Prompt / output ? / 128 tokens Context 8192 Concurrency Not reported Date Not reported Full record →
View ReportGeneric LLM	Qwen2.5-7B-InstructQ8_0Model ref. ↗	Token speed	—	886 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 Engine llama.cpp Backend HIP / ROCm 7.2.0 Harness Not reported Prompt / output 128 / ? tokens Context 8192 Concurrency Not reported Date Not reported Full record →
View ReportGeneric LLM	Qwen2.5-7B-InstructQ8_0Model ref. ↗	Token speed	—	1,153 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 Engine llama.cpp Backend HIP / ROCm 7.2.0 Harness Not reported Prompt / output 256 / ? tokens Context 8192 Concurrency Not reported Date Not reported Full record →
View ReportGeneric LLM	Qwen2.5-7B-InstructQ8_0Model ref. ↗	Token speed	—	1,392 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 Engine llama.cpp Backend HIP / ROCm 7.2.0 Harness Not reported Prompt / output 512 / ? tokens Context 8192 Concurrency Not reported Date Not reported Full record →
View ReportGeneric LLM	Qwen2.5-7B-InstructQ8_0Model ref. ↗	Token speed	—	—	69.5 tok/sGeneration · mean · per request	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Ubuntu 24.04.4 Engine llama.cpp Backend HIP / ROCm 7.2.0 Harness Not reported Prompt / output ? / 128 tokens Context 8192 Concurrency Not reported Date Not reported Full record →

Quantizations and software

Quantizations: Q4_K_M, Q5_K_M, Q6_K, Q8_0
Engines: llama.cpp

Explore all 18 results →

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

GPU benchmark pages: R9700