Mistral
Leanstral 119B A6B
現行
99ダウンロード157いいねMar 2026公開日256K トークンコンテキストApache 2.0ライセンス84 優秀品質
Leanstral 119B A6B (119B parameters) requires approximately 84.4 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 6.5B 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 98 GB of VRAM.
はじめに
— コピー&ペーストでローカル実行Copy-paste commands to run Leanstral 119B A6B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "mistralai/Leanstral-2603" \
--hf-file "Leanstral-2603-Q4_K_M.gguf" \
-c 4096 -ngl 99Quick specs
Parameters119B (6.5B active)
Architecturemoe (MoE)
Context256K tokens
Modalitytext+vision
Min RAM46.4 GB
Rec. RAM72.6 GB (Q4_K_M)
LicenseApache 2.0
FamilyMistral Small
✓ Vision✓ Code✓ Reasoning
About this model
- •119B total params with 6.5B active per token
- •Specialized for proof engineering and code-agent workflows
- •256K context with multimodal text and image input
関連モデル
おすすめ
最適なハードウェア
Leanstral 119B A6Bのおすすめ
このモデルを実行
量子化オプション
量子化レベル別VRAM推定値
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 46.4 GB | Low | — |
Q3_K_S | 3 | 58.3 GB | Low | — |
NVFP4 | 4 | 66.6 GB | Medium | — |
Q4_K_M | 4 | 72.6 GB | Medium | — |
Q5_K_M | 5 | 85.7 GB | High | — |
Q6_K | 6 | 97.6 GB | High | — |
Q8_0 | 8 | 127.3 GB | Very High | — |
F16 | 16 | 244.0 GB | Maximum | — |
ハードウェア互換性
全ハードウェアの適合度推定
Computing compatibility...
メモリ内訳
Reference: RTX 2060 6GB
Weights72.6 GB
KV Cache8.8 GB
Runtime2.4 GB
Headroom0.6 GB
よくある質問
FAQ — Leanstral 119B A6B
関連項目