DeepReinforce
Ornith 1.0 35B A3B
前沿
231.3K下载量348点赞Jun 2026发布日期262K tokens上下文MIT许可证72 优秀质量
Ornith 1.0 35B A3B (35.099998474121094B parameters) requires approximately 23.2 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 3B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 27 GB of VRAM.
快速开始
— 复制粘贴即可本地运行Copy-paste commands to run Ornith 1.0 35B A3B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "deepreinforce-ai/Ornith-1.0-35B" \
--hf-file "Ornith-1.0-35B-Q4_K_M.gguf" \
-c 4096 -ngl 99Quick specs
Parameters35.1B (3B active)
Architecturemoe (MoE)
Context262K tokens
Modalitytext
Min RAM13.7 GB
Rec. RAM21.4 GB (Q4_K_M)
LicenseMIT
FamilyOrnith
✓ Code✓ Reasoning
About this model
- •Self-improving agentic RL: jointly refines solution generation and reasoning scaffolds.
- •35B MoE with only ~3B activated per token — the lightweight member of the Ornith family.
- •Hybrid linear-attention + full-attention (1-in-4 layers) for reduced KV-cache cost.
- •262K context, tuned for single-GPU agentic coding.
快速推荐
最佳硬件
Ornith 1.0 35B A3B 的最佳选择
运行此模型
量化选项
各量化级别的 VRAM 估算
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 13.7 GB | Low | — |
Q3_K_S | 3 | 17.2 GB | Low | — |
NVFP4 | 4 | 19.7 GB | Medium | — |
Q4_K_M | 4 | 21.4 GB | Medium | — |
Q5_K_M | 5 | 25.3 GB | High | — |
Q6_K | 6 | 28.8 GB | High | — |
Q8_0 | 8 | 37.6 GB | Very High | — |
F16 | 16 | 72.0 GB | Maximum | — |
硬件兼容性
全部硬件的适配估算
Computing compatibility...
内存详细分析
Reference: RTX 2060 6GB
Weights21.4 GB
KV Cache0.3 GB
Runtime0.9 GB
Headroom0.6 GB
常见问题
FAQ — Ornith 1.0 35B A3B
另请参阅