Quel modèle pour Laptop 8 Go RAM ?
6 Go utilisables pour le modèle (80 % de la RAM, exécution CPU). 30 modèles open-weight tiennent en mémoire.
La marge sert au contexte : comptez ~1 Go par 8k tokens pour un modèle 7B. Une marge faible = contexte court.
| Modèle | Elo | Quantization | RAM requise | Marge | Vitesse | Lancer |
|---|---|---|---|---|---|---|
| Gemma 3 4BGoogle · 4B | 1303 | Q4_K_M | 5 Go | +1 Go | lent (CPU) | ollama run gemma3:4b |
| Llama 3.2 3BMeta · 3.21B | 1166 | Q8_0 | 6 Go | +0 Go | lent (CPU) | ollama run llama3.2:3b |
| Llama 3.2 1BMeta · 1.24B | 1111 | FP16 | 5 Go | +1 Go | lent (CPU) | ollama run llama3.2:1b |
| Kokoro-82MHexgrad · 0.08B | — | FP16 | 2 Go | +4 Go | lent (CPU) | Hugging Face ↗ |
| ChatterboxResemble AI · 0.5B | — | FP16 | 3 Go | +3 Go | lent (CPU) | Hugging Face ↗ |
| Parakeet TDT 0.6B v3NVIDIA · 0.6B | — | FP16 | 3 Go | +3 Go | lent (CPU) | Hugging Face ↗ |
| Qwen3 0.6BAlibaba · 0.6B | — | FP16 | 3 Go | +3 Go | lent (CPU) | ollama run qwen3:0.6b |
| TripoSRStability AI · 0.5B | — | FP16 | 3 Go | +3 Go | lent (CPU) | Hugging Face ↗ |
| Gemma 3 1BGoogle · 1B | — | FP16 | 4 Go | +2 Go | lent (CPU) | ollama run gemma3:1b |
| Phi-4 MiniMicrosoft · 3.8B | — | Q4_K_M | 4 Go | +2 Go | lent (CPU) | ollama run phi4-mini |
| Stable Fast 3DStability AI · 1B | — | FP16 | 4 Go | +2 Go | lent (CPU) | Hugging Face ↗ |
| CogVideoX 5BZhipu AI · 5B | — | Q4_K_M | 5 Go | +1 Go | lent (CPU) | Hugging Face ↗ |
| FLUX.2 [klein] 4BBlack Forest Labs · 4B | — | Q4_K_M | 5 Go | +1 Go | lent (CPU) | Hugging Face ↗ |
| Gemma 4 E4BGoogle · 4B | — | Q4_K_M | 5 Go | +1 Go | lent (CPU) | Hugging Face ↗ |
| Qwen3 4BAlibaba · 4.02B | — | Q4_K_M | 5 Go | +1 Go | lent (CPU) | ollama run qwen3:4b |
| TRELLISMicrosoft · 1.2B | — | FP16 | 5 Go | +1 Go | lent (CPU) | Hugging Face ↗ |
| TRELLIS.2Microsoft · 4B | — | Q4_K_M | 5 Go | +1 Go | lent (CPU) | Hugging Face ↗ |
| Wan 2.2 5BAlibaba · 5B | — | Q4_K_M | 5 Go | +1 Go | lent (CPU) | Hugging Face ↗ |
| Whisper large-v3OpenAI · 1.55B | — | FP16 | 5 Go | +1 Go | lent (CPU) | Hugging Face ↗ |
| Dia 1.6BNari Labs · 1.6B | — | FP16 | 6 Go | +0 Go | lent (CPU) | Hugging Face ↗ |
| Gemma 4 E2BGoogle · 2B | — | FP16 | 6 Go | +0 Go | lent (CPU) | Hugging Face ↗ |
| Granite 4.1 3BIBM · 3B | — | Q8_0 | 6 Go | +0 Go | lent (CPU) | Hugging Face ↗ |
| Hunyuan3D 2.1Tencent · 3B | — | Q8_0 | 6 Go | +0 Go | lent (CPU) | Hugging Face ↗ |
| Lucie 7BOpenLLM France · 6.7B | — | Q4_K_M | 6 Go | +0 Go | lent (CPU) | Hugging Face ↗ |
| Ministral 3 3BMistral AI · 3B | — | Q8_0 | 6 Go | +0 Go | lent (CPU) | Hugging Face ↗ |
| OLMo 3 7BAllen AI · 7B | — | Q4_K_M | 6 Go | +0 Go | lent (CPU) | Hugging Face ↗ |
| Orpheus 3BCanopy Labs · 3B | — | Q8_0 | 6 Go | +0 Go | lent (CPU) | Hugging Face ↗ |
| SmolLM3 3BHugging Face · 3.1B | — | Q8_0 | 6 Go | +0 Go | lent (CPU) | Hugging Face ↗ |
| Voxtral Mini 3BMistral AI · 3B | — | Q8_0 | 6 Go | +0 Go | lent (CPU) | Hugging Face ↗ |
| Z-Image TurboAlibaba · 6B | — | Q4_K_M | 6 Go | +0 Go | lent (CPU) | Hugging Face ↗ |