Benchmark llama.cpp sur Tuxedo 17
-
Donc on est passé de : CPU vs CUDA
pp512 : 303.04 t/s => 10984.34 t/s ( x36 env. )
tg128 : 46.90 t/s => 225.56 t/s ( x5 env. ) -
Chargement de modèle sur : https://huggingface.co/unsloth
-
Test du modèle : Qwen3.6-35B-A3B-UD-Q4_K_M.gguf
# llama-server -m /models/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf 0.01.777.599 I log_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.01.777.603 I device_info: 0.01.868.348 I - CUDA0 : NVIDIA GeForce RTX 3060 Laptop GPU (5806 MiB, 5674 MiB free) 0.01.868.364 I - CPU : 11th Gen Intel(R) Core(TM) i7-11800H @ 2.30GHz (64044 MiB, 64044 MiB free) 0.01.868.506 I system_info: n_threads = 8 (n_threads_batch = 8) / 16 | CUDA : ARCHS = 750,800,860,890,900,1200,1210 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 | 0.01.868.514 I srv llama_server: n_parallel is set to auto, using n_parallel = 4 and kv_unified = true 0.01.868.566 I srv init: running without SSL 0.01.868.646 I srv init: using 15 threads for HTTP server 0.01.869.153 I srv start: binding port with default address family 0.01.870.425 I srv llama_server: loading model 0.01.870.434 I srv load_model: loading model '/moddels/Qwen3.6-35B-A3B-UD-Q4_K_M.gguf' -
Nouveau test :
# curl -L --fail -o /models/qwen2.5-1.5b-instruct-q4_k_m.gguf https://huggingface.co/bartowski/Qwen2.5-1.5B-Instruct-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-Q4_K_M.gguf # llama-server -m /models/qwen2.5-1.5b-instruct-q4_k_m.gguf --host "0.0.0.0" --port "8080" --ctx-size "4096" --threads 8 --alias qwen2.5-1.5bhttp://127.0.0.1:8080/health => OK.
-
Test :
$ curl -fsS http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{ "model": "qwen2.5-1.5b", "messages": [ {"role": "system", "content": "Tu es un assistant DevOps qui répond en français en une phrase."}, {"role": "user", "content": "Quelle commande systemd affiche les services actifs ?"} ], "temperature": 0.2, "max_tokens": 80 }' | jq { "choices": [ { "finish_reason": "stop", "index": 0, "message": { "role": "assistant", "content": "systemctl list-units --active" } } ], "created": 1781775300, "model": "qwen2.5-1.5b", "system_fingerprint": "b9687-b4024af6c", "object": "chat.completion", "usage": { "completion_tokens": 8, "prompt_tokens": 38, "total_tokens": 46, "prompt_tokens_details": { "cached_tokens": 37 } }, "id": "chatcmpl-mXP4t0noHYBKTaBSnZfxFdoTycVt42zC", "timings": { "cache_n": 37, "prompt_n": 1, "prompt_ms": 21.161, "prompt_per_token_ms": 21.161, "prompt_per_second": 47.25674590047729, "predicted_n": 8, "predicted_ms": 40.424, "predicted_per_token_ms": 5.053, "predicted_per_second": 197.90223629527014 } } -
Fichier /models/
# du -sh /models/* 769M /models/gemma-3-1b-it-Q4_K_M.gguf 889M /models/mmproj-BF16.gguf 858M /models/mmproj-F16.gguf 1,3G /models/mmproj-F32.gguf 941M /models/qwen2.5-1.5b-instruct-q4_k_m.gguf 1,2G /models/Qwen3.5-2B-Q4_0.gguf 16G /models/Qwen3.6-27B-Q4_K_M.gguf 21G /models/Qwen3.6-35B-A3B-UD-Q4_K_M.ggufChangement du modèle :
-m /models/Qwen3.5-2B-Q4_0.gguf --mmproj /models/mmproj-F32.gguf \Par
-m /models/Qwen3.6-27B-Q4_K_M.gguf --mmproj /models/mmproj-BF16.ggufLiens :
https://huggingface.co/unsloth/Qwen3.6-27B-MTP-GGUF
https://huggingface.co/unsloth/Qwen3.6-27B-GGUF/blob/main/mmproj-BF16.gguf -
Mémoire :
# nvidia-smi Tue Jun 30 10:59:11 2026 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 595.71.05 Driver Version: 595.71.05 CUDA Version: 13.2 | +-----------------------------------------+------------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+========================+======================| | 0 NVIDIA GeForce RTX 3060 ... Off | 00000000:01:00.0 Off | N/A | | N/A 53C P0 28W / 115W | 4007MiB / 6144MiB | 0% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | 0 N/A N/A 1820494 G /usr/lib/xorg/Xorg 4MiB | | 0 N/A N/A 1832019 C /usr/local/bin/llama-server 3984MiB | +-----------------------------------------------------------------------------------------+ -
Augmentation du contexte :
-m /models/Qwen3.6-27B-Q4_K_M.gguf --mmproj /models/mmproj-BF16.gguf --ctx-size 80000 -
Pendant l’utilisation :
# nvidia-smi Tue Jun 30 12:35:32 2026 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 595.71.05 Driver Version: 595.71.05 CUDA Version: 13.2 | +-----------------------------------------+------------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+========================+======================| | 0 NVIDIA GeForce RTX 3060 ... Off | 00000000:01:00.0 Off | N/A | | N/A 55C P0 28W / 115W | 4621MiB / 6144MiB | 0% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | 0 N/A N/A 1820494 G /usr/lib/xorg/Xorg 4MiB | | 0 N/A N/A 1845119 C /usr/local/bin/llama-server 4598MiB | +-----------------------------------------------------------------------------------------+ -
Ce message a été supprimé !
-
Ce message a été supprimé !
Bonjour ! Vous semblez intéressé par cette conversation, mais vous n’avez pas encore de compte.
Marre de refaire défiler les mêmes messages ? Créez un compte pour retrouver votre position, recevoir des notifications des nouvelles réponses, sauvegarder vos favoris et voter pour les messages que vous appréciez.
Grâce à votre participation, ce message peut devenir encore meilleur 💗
S'inscrire Se connecter