Ministral-3-14B-Instruct-2512 on AMD GPUs

166 results · 3 sources · 166 measurements

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

Documented results

24 selected tests


View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed512 input tokens · 0 output tokens · 0 existing KV tokens	—	801.06 tok/sPrefill · mean · per request	—	1 × Ryzen AI Max+ 395Single GPU · Unified memory Configuration Memory Unified memory OS Fedora Linux 43 (Workstation Edition) Engine llama.cpp Backend ROCm / rocm-7_2_3 Harness llama-bench Prompt / output 512 / 0 tokens Context Not reported Concurrency 1 Date 2026-05-16 Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed2,048 input tokens · 16,384 existing KV tokens	—	757.63 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Linux (inferred; distribution unreported) (inferred) Engine llama.cpp Backend rocm-7-nightly Harness llama-bench Prompt / output 2048 / ? tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed2,048 input tokens · 16,384 existing KV tokens	—	1,177.72 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Fedora 42 — Linux 6.15.9-201.fc42.x86_64 (Sat Aug 2 11:37:34 UTC 2025) Engine llama.cpp Backend rocm6_4_4 Harness llama-bench Prompt / output 2048 / ? tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed0 input tokens · 128 output tokens · 0 existing KV tokens	—	—	8.5 tok/sGeneration · mean · per request	1 × Ryzen AI Max+ 395Single GPU · Unified memory Configuration Memory Unified memory OS Fedora Linux 43 (Workstation Edition) Engine llama.cpp Backend ROCm / rocm-7_2_3 Harness llama-bench Prompt / output 0 / 128 tokens Context Not reported Concurrency 1 Date 2026-05-16 Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed32 output tokens · 16,384 existing KV tokens	—	—	20.22 tok/sGeneration · mean · per request	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Linux (inferred; distribution unreported) (inferred) Engine llama.cpp Backend rocm-7-nightly Harness llama-bench Prompt / output ? / 32 tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed32 output tokens · 16,384 existing KV tokens	—	—	20.55 tok/sGeneration · mean · per request	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Fedora 42 — Linux 6.15.9-201.fc42.x86_64 (Sat Aug 2 11:37:34 UTC 2025) Engine llama.cpp Backend rocm6_4_4 Harness llama-bench Prompt / output ? / 32 tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed2,048 input tokens · 0 output tokens · 32,768 existing KV tokens	—	349.46 tok/sPrefill · mean · per request	—	1 × Ryzen AI Max+ 395Single GPU · Unified memory Configuration Memory Unified memory OS Fedora Linux 43 (Workstation Edition) Engine llama.cpp Backend ROCm / rocm-7_2_3 Harness llama-bench Prompt / output 2048 / 0 tokens Context Not reported Concurrency 1 Date 2026-05-16 Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed2,048 input tokens · 32,768 existing KV tokens	—	449.05 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Linux (inferred; distribution unreported) (inferred) Engine llama.cpp Backend rocm-7-nightly Harness llama-bench Prompt / output 2048 / ? tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed2,048 input tokens · 32,768 existing KV tokens	—	754.24 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Fedora 42 — Linux 6.15.9-201.fc42.x86_64 (Sat Aug 2 11:37:34 UTC 2025) Engine llama.cpp Backend rocm6_4_4 Harness llama-bench Prompt / output 2048 / ? tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed0 input tokens · 32 output tokens · 32,768 existing KV tokens	—	—	7.12 tok/sGeneration · mean · per request	1 × Ryzen AI Max+ 395Single GPU · Unified memory Configuration Memory Unified memory OS Fedora Linux 43 (Workstation Edition) Engine llama.cpp Backend ROCm / rocm-7_2_3 Harness llama-bench Prompt / output 0 / 32 tokens Context Not reported Concurrency 1 Date 2026-05-16 Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed32 output tokens · 32,768 existing KV tokens	—	—	18.64 tok/sGeneration · mean · per request	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Linux (inferred; distribution unreported) (inferred) Engine llama.cpp Backend rocm-7-nightly Harness llama-bench Prompt / output ? / 32 tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed32 output tokens · 32,768 existing KV tokens	—	—	18.9 tok/sGeneration · mean · per request	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Fedora 42 — Linux 6.15.9-201.fc42.x86_64 (Sat Aug 2 11:37:34 UTC 2025) Engine llama.cpp Backend rocm6_4_4 Harness llama-bench Prompt / output ? / 32 tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed2,048 input tokens · 0 output tokens · 65,536 existing KV tokens	—	209.94 tok/sPrefill · mean · per request	—	1 × Ryzen AI Max+ 395Single GPU · Unified memory Configuration Memory Unified memory OS Fedora Linux 43 (Workstation Edition) Engine llama.cpp Backend ROCm / rocm-7_2_3 Harness llama-bench Prompt / output 2048 / 0 tokens Context Not reported Concurrency 1 Date 2026-05-16 Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed512 input tokens · 0 existing KV tokens	—	2,767.12 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Linux (inferred; distribution unreported) (inferred) Engine llama.cpp Backend rocm-7-nightly Harness llama-bench Prompt / output 512 / ? tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed512 input tokens · 0 existing KV tokens	—	2,452.71 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Fedora 42 — Linux 6.15.9-201.fc42.x86_64 (Sat Aug 2 11:37:34 UTC 2025) Engine llama.cpp Backend rocm6_4_4 Harness llama-bench Prompt / output 512 / ? tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed0 input tokens · 32 output tokens · 65,536 existing KV tokens	—	—	6.14 tok/sGeneration · mean · per request	1 × Ryzen AI Max+ 395Single GPU · Unified memory Configuration Memory Unified memory OS Fedora Linux 43 (Workstation Edition) Engine llama.cpp Backend ROCm / rocm-7_2_3 Harness llama-bench Prompt / output 0 / 32 tokens Context Not reported Concurrency 1 Date 2026-05-16 Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed128 output tokens · 0 existing KV tokens	—	—	22.21 tok/sGeneration · mean · per request	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Linux (inferred; distribution unreported) (inferred) Engine llama.cpp Backend rocm-7-nightly Harness llama-bench Prompt / output ? / 128 tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed128 output tokens · 0 existing KV tokens	—	—	22.56 tok/sGeneration · mean · per request	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Fedora 42 — Linux 6.15.9-201.fc42.x86_64 (Sat Aug 2 11:37:34 UTC 2025) Engine llama.cpp Backend rocm6_4_4 Harness llama-bench Prompt / output ? / 128 tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed512 input tokens · 0 output tokens · 0 existing KV tokens	—	762.49 tok/sPrefill · mean · per request	—	1 × Ryzen AI Max+ 395Single GPU · Unified memory Configuration Memory Unified memory OS Fedora Linux 43 (Workstation Edition) Engine llama.cpp Backend ROCm / rocm6_4_4 Harness llama-bench Prompt / output 512 / 0 tokens Context Not reported Concurrency 1 Date 2026-05-16 Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed2,048 input tokens · 16,384 existing KV tokens	—	279.8 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Linux (inferred; distribution unreported) (inferred) Engine llama.cpp Backend rocm-7-nightly Harness llama-bench Prompt / output 2048 / ? tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed2,048 input tokens · 16,384 existing KV tokens	—	1,363.79 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Fedora 42 — Linux 6.15.9-201.fc42.x86_64 (Sat Aug 2 11:37:34 UTC 2025) Engine llama.cpp Backend rocm7_2_2 Harness llama-bench Prompt / output 2048 / ? tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed0 input tokens · 128 output tokens · 0 existing KV tokens	—	—	8.49 tok/sGeneration · mean · per request	1 × Ryzen AI Max+ 395Single GPU · Unified memory Configuration Memory Unified memory OS Fedora Linux 43 (Workstation Edition) Engine llama.cpp Backend ROCm / rocm6_4_4 Harness llama-bench Prompt / output 0 / 128 tokens Context Not reported Concurrency 1 Date 2026-05-16 Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed32 output tokens · 16,384 existing KV tokens	—	—	20.23 tok/sGeneration · mean · per request	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Linux (inferred; distribution unreported) (inferred) Engine llama.cpp Backend rocm-7-nightly Harness llama-bench Prompt / output ? / 32 tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	Ministral-3-14B-Instruct-2512BF16Model ref. ↗	Token speed32 output tokens · 16,384 existing KV tokens	—	—	20.34 tok/sGeneration · mean · per request	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Fedora 42 — Linux 6.15.9-201.fc42.x86_64 (Sat Aug 2 11:37:34 UTC 2025) Engine llama.cpp Backend rocm7_2_2 Harness llama-bench Prompt / output ? / 32 tokens Context Not reported Concurrency Not reported Date Not reported Full record →

Quantizations and software

Quantizations: BF16
Engines: llama.cpp

Explore all 166 results →

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

GPU benchmark pages: R9700 · Ryzen AI Max+ 395