✅ LÄUFT NATIV IN FP16 & ALLEN QUANTISIERUNGEN
Qwen2.5-Coder-32B-Instruct on AMD Instinct MI300X 192GB (192GB VRAM)
In 4-bit GGUF Q4_K_M, Qwen2.5-Coder-32B-Instruct consumes 21.23 GB (18.73 GB weights + 2 GB KV cache at 8K context), achieving ~184.1 tokens/sec decode and ~10373 tokens/sec prefill.
🎛️ Interaktiver VRAM-, Kontext- & Offload-Konfigurator
📊 Echtzeit-Speicher- & Performance-Telemetrie
21.23 GB / 192 GB
🟦 Modellgewichte: 18.73 GB
🟪 KV-Cache: 2 GB
🟨 Engine-Puffer: 0.49 GB
Benötigter GPU-VRAM21.23 GB
Benötigter System-RAM (CPU)0.00 GB
Verfügbarer Hardware-VRAM192 GB (1x AMD Instinct MI300X 192GB)
VRAM-Reserve / Defizit170.77 GB
Geschätzte Decode-Geschwindigkeit~184.1 tokens/sec
Geschätzte Prefill-Geschwindigkeit~10373 tokens/sec
Time-to-First-Token (4K Prompt)~395 ms
Transformer-TopologieDense-GQA (64L, 8/40 KV/Q heads)
🚀 Startbefehl (vLLM / llama.cpp / Ollama)
ollama run qwen2.5-coder:32b # Or llama.cpp server (8K context, Flash Attention): llama-server -hf Qwen/Qwen2.5-Coder-32B-Instruct-GGUF -c 8192 -ngl 99 -fa
CLOUD-GPU PREISVERGLEICH & MIETEN-VS-KAUFEN RECHNER
Nicht genug lokaler VRAM? Cloud-GPU in 60 Sekunden starten (Qwen2.5-Coder-32B-Instruct: 21.23 GB in 4-bit)
Recommended Cloud Tier: RTX 4090 (24GB) · Full FP16 Needs: 63.96 GB
Amortisationszeit (Kauf vs. Miete): ~32 months (vs $19,500 hardware)
| Cloud Provider | RTX 4090 (24GB) | A100 (80GB) | H100 (80GB) | Est. Monthly Cost (4h/day) | Free Credit / Trial | Deploy |
|---|---|---|---|---|---|---|
| RunPod | $0.44 / hr | $1.39 / hr | $2.39 / hr | $52.80 / mo | Instant PyTorch / vLLM Templates + Serverless GPU | Auf RunPod starten → |
| Vast.ai | $0.29 / hr | $0.95 / hr | $1.79 / hr | $34.80 / mo | Save 50–70% on RTX 4090 / 5090 / A100 rentals | Spot-GPU mieten → |
| Vultr Cloud GPU | — | $1.79 / hr | $2.69 / hr | $214.80 / mo (A100) | $300 Free Credit | $300 Guthaben sichern → |
| DigitalOcean GPU | — | — | $2.99 / hr | $358.80 / mo (H100) | $200 Free Credit (60d) | $200 Startguthaben → |
Alle Quantisierungsstufen im Detail: Qwen2.5-Coder-32B-Instruct × AMD Instinct MI300X 192GB
| Quantization Format | Core / Emb BPW | Weights (GiB) | KV Cache (8K) | Total VRAM | 1x AMD Instinct MI300X 192GB (192GB) | Decode / Prefill | Min GPUs |
|---|---|---|---|---|---|---|---|
| FP16 / BF16 (Unquantized) | 16 / 16 | 61.02 GB | 2 GB | 63.51 GB | Ja (33%) | ~55.6 / 10373 tok/s | 1x |
| FP8 (W8A8 / E4M3) | 8.25 / 8.5 | 31.51 GB | 2 GB | 34 GB | Ja (18%) | ~107.8 / 10373 tok/s | 1x |
| GGUF Q8_0 (8.50 bpw) | 8.5 / 8.5 | 32.42 GB | 2 GB | 34.91 GB | Ja (18%) | ~104.6 / 10373 tok/s | 1x |
| GGUF Q6_K (6.56 bpw) | 6.56 / 6.56 | 25.02 GB | 2 GB | 27.51 GB | Ja (14%) | ~135.6 / 10373 tok/s | 1x |
| GGUF Q5_K_M (5.69 bpw) | 5.69 / 6.56 | 21.86 GB | 2 GB | 24.35 GB | Ja (13%) | ~156.3 / 10373 tok/s | 1x |
| GGUF Q4_K_M / AWQ (4.83 bpw) | 4.83 / 6.56 | 18.73 GB | 2 GB | 21.23 GB | Ja (11%) | ~184.1 / 10373 tok/s | 1x |
| GGUF IQ4_XS (4.25 bpw) | 4.25 / 5.5 | 16.44 GB | 2 GB | 18.93 GB | Ja (10%) | ~209.3 / 10373 tok/s | 1x |
| GGUF Q3_K_M (3.91 bpw) | 3.91 / 5 | 15.11 GB | 2 GB | 17.6 GB | Ja (9%) | ~227.5 / 10373 tok/s | 1x |
Dieses Modell auf anderen GPUs testen
Qwen2.5-Coder-32B-Instruct on NVIDIA RTX 5090 (32GB)Qwen2.5-Coder-32B-Instruct on NVIDIA RTX 4090 (24GB)Qwen2.5-Coder-32B-Instruct on NVIDIA RTX 5080 (16GB)Qwen2.5-Coder-32B-Instruct on NVIDIA RTX 4080 Super (16GB)Qwen2.5-Coder-32B-Instruct on NVIDIA RTX 4070 Ti Super (16GB)Qwen2.5-Coder-32B-Instruct on NVIDIA RTX 3090 (24GB)Qwen2.5-Coder-32B-Instruct on NVIDIA RTX 4060 Ti 16GB (16GB)Qwen2.5-Coder-32B-Instruct on NVIDIA RTX 3060 12GB (12GB)Qwen2.5-Coder-32B-Instruct on NVIDIA RTX 6000 Ada (48GB)Qwen2.5-Coder-32B-Instruct on NVIDIA RTX A6000 (48GB)
Weitere Modelle auf dieser GPU
DeepSeek-R1 671B (MoE) on AMD Instinct MI300X 192GBDeepSeek-V3-0324 671B (MoE) on AMD Instinct MI300X 192GBDeepSeek-R1-Distill-Llama-70B on AMD Instinct MI300X 192GBDeepSeek-R1-Distill-Qwen-32B on AMD Instinct MI300X 192GBDeepSeek-R1-Distill-Qwen-14B on AMD Instinct MI300X 192GBDeepSeek-R1-Distill-Llama-8B on AMD Instinct MI300X 192GBDeepSeek-R1-Distill-Qwen-7B on AMD Instinct MI300X 192GBQwen3-235B-A22B (MoE) on AMD Instinct MI300X 192GBQwen3-30B-A3B (MoE) on AMD Instinct MI300X 192GBQwen3-32B on AMD Instinct MI300X 192GB