Poolside
Laguna XS 2.1
最先端
22.5Kダウンロード170いいねJun 2026公開日262K トークンコンテキストOpenMDW 1.1ライセンス75 優秀品質
Laguna XS 2.1 (33.400001525878906B parameters) requires approximately 22.5 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 26 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 Laguna XS 2.1 on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "poolside/Laguna-XS-2.1" \
--hf-file "Laguna-XS-2.1-Q4_K_M.gguf" \
-c 4096 -ngl 99Quick specs
Parameters33.4B (3B active)
Architecturemoe (MoE)
Context262K tokens
Modalitytext
Min RAM13 GB
Rec. RAM20.4 GB (Q4_K_M)
LicenseOpenMDW 1.1
FamilyLaguna
✓ Code✓ Reasoning
About this model
- •33B total / ~3B active — runs comfortably on a single 24GB GPU at Q4.
- •Same router and attention recipe as Laguna S 2.1, at a quarter of the size.
- •262K context with 1:3 global-to-sliding-window attention (window 512).
- •Targeted at agentic coding and long-horizon tool use.
関連モデル
おすすめ
最適なハードウェア
Laguna XS 2.1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 |
|---|---|---|---|---|
Q1_0_G128 | 1.125 | 4.8 GB | Very Low | — |
Q2_0_G128 | 1.71 | 8.9 GB | Low | — |
Q2_K | 2 | 13.0 GB | Low | — |
Q3_K_S | 3 | 16.4 GB | Low | — |
NVFP4 | 4 | 18.7 GB | Medium | — |
Q4_K_M | 4 | 20.4 GB | Medium | — |
Q5_K_M | 5 | 24.0 GB | High | — |
Q6_K | 6 | 27.4 GB | High | — |
Q8_0 | 8 | 35.7 GB | Very High | — |
F16 | 16 | 68.5 GB | Maximum | — |
Quality benchmarks
Laguna XS 2.1 benchmark scores
Coding
SWE-bench Verified70.9%
HumanEval+—
Aider Polyglot—
LiveCodeBench—
Source: official · 2026-06-20
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
Weights20.4 GB
KV Cache0.6 GB
Runtime0.9 GB
Headroom0.6 GB
よくある質問
FAQ — Laguna XS 2.1
関連項目