DefiledAI Research
MODEL DATABASE
Open-weight models with quantization options, VRAM requirements, and abliterated variant availability.
Llamaby Meta
ACTIVE| Model | Params | Context | Min VRAM | License | Quants | Abliterated |
|---|---|---|---|---|---|---|
| Llama 3.1 8B | 8B | 128K | 6GB | Llama 3 | Q4_K_MQ5_K_MQ8_0F16 | ✓ AVAILABLE ↗ |
| Llama 3.1 70B | 70B | 128K | 40GB | Llama 3 | Q2_KQ4_K_MQ5_K_MIQ3_M | ✓ AVAILABLE ↗ |
| Llama 3.1 405B | 405B | 128K | 240GB | Llama 3 | Q2_KIQ1_M | — |
Qwenby Alibaba
ACTIVE| Model | Params | Context | Min VRAM | License | Quants | Abliterated |
|---|---|---|---|---|---|---|
| Qwen 3 7B | 7B | 32K | 6GB | Apache 2.0 | Q4_K_MQ5_K_MQ8_0 | ✓ AVAILABLE ↗ |
| Qwen 3 14B | 14B | 32K | 10GB | Apache 2.0 | Q4_K_MQ5_K_M | ✓ AVAILABLE ↗ |
| Qwen 3 72B | 72B | 32K | 40GB | Apache 2.0 | Q2_KQ4_K_MQ5_K_M | ✓ AVAILABLE ↗ |
DeepSeekby DeepSeek
ACTIVE| Model | Params | Context | Min VRAM | License | Quants | Abliterated |
|---|---|---|---|---|---|---|
| DeepSeek R1 7B | 7B | 32K | 6GB | MIT | Q4_K_MQ8_0 | ✓ AVAILABLE ↗ |
| DeepSeek R1 70B | 70B | 32K | 40GB | MIT | Q4_K_MIQ3_M | ✓ AVAILABLE ↗ |
| DeepSeek V3 | 671B MoE | 128K | Multi-GPU | MIT | Q2_KIQ1_M | — |
Mistralby Mistral AI
ACTIVE| Model | Params | Context | Min VRAM | License | Quants | Abliterated |
|---|---|---|---|---|---|---|
| Mistral 7B v0.3 | 7B | 32K | 6GB | Apache 2.0 | Q4_K_MQ5_K_MQ8_0F16 | ✓ AVAILABLE ↗ |
| Mixtral 8x7B | 56B MoE | 32K | 24GB | Apache 2.0 | Q4_K_MQ5_K_M | ✓ AVAILABLE ↗ |
| Mixtral 8x22B | 141B MoE | 64K | 48GB | Apache 2.0 | Q2_KQ4_K_M | — |
Gemmaby Google
ACTIVE| Model | Params | Context | Min VRAM | License | Quants | Abliterated |
|---|---|---|---|---|---|---|
| Gemma 2 2B | 2B | 8K | 2GB | Gemma | Q4_K_MQ8_0F16 | — |
| Gemma 2 9B | 9B | 8K | 6GB | Gemma | Q4_K_MQ5_K_MQ8_0 | ✓ AVAILABLE ↗ |
| Gemma 2 27B | 27B | 8K | 16GB | Gemma | Q4_K_MQ5_K_M | ✓ AVAILABLE ↗ |
Phiby Microsoft
ACTIVE| Model | Params | Context | Min VRAM | License | Quants | Abliterated |
|---|---|---|---|---|---|---|
| Phi-3 Mini | 3.8B | 128K | 3GB | MIT | Q4_K_MQ8_0F16 | — |
| Phi-3 Medium | 14B | 128K | 10GB | MIT | Q4_K_MQ5_K_M | ✓ AVAILABLE ↗ |
Want full ratings, quality scores, and notes? Visit the Uncensored Database →