Laguna S 2.1 hardware requirements
What is Laguna S 2.1?
Laguna S 2.1 is a mixture-of-experts model from Poolside, released in July 2026 and designed for agentic coding and long-horizon software work. It has about 118B parameters in total but roughly 8B active per token, a 1M-token context window, and a thinking mode that can be turned off per request. The OpenMDW-1.1 license allows commercial use.
About the model
- Parameters
- 117.56B total · 8B active (MoE)
- Attention
- Sliding-window attention
- Max context
- 1,048,576 tokens
- Released
- 2026-07-13
- Model card
- Laguna S 2.1 on Hugging Face
GGUF files
| Quant | File size | Quality | Published by |
|---|---|---|---|
| Q4_K_Mbaseline | 67.66 GB | Good balance | llama.cpp team · ggml-org |
| Q8_0 | 125.02 GB | Near-lossless | llama.cpp team · ggml-org |
Memory needed by quant and context
| Quant | 4k | 8k | 16k | 32k | 64k | 128k | 256k |
|---|---|---|---|---|---|---|---|
| Q4_K_M | 68.2 | 68.5 | 68.9 | 69.9 | 71.8 | 75.6 | 83.3 |
| Q8_0 | 125.4 | 125.7 | 126.1 | 127.1 | 129.0 | 132.8 | 140.5 |
Which GPUs can run Laguna S 2.1?
How to read the verdicts
- Runs great
- Fully on the GPU at 20 tok/s or more
- Runs well
- Fully on the GPU at 8–20 tok/s; MoE experts in system RAM at 20 tok/s or more; or at least 90% on the GPU at 8 tok/s or more
- Runs slowly
- 2–8 tok/s; CPU-only; less than 90% on the GPU; or MoE experts in system RAM below 20 tok/s
- Won't run
- Does not fit, or under 2 tok/s
Filter this list by budget, type and context in the calculator
Scroll sideways to see every column.
| Hardware | Verdict | Speed | Quant | Memory | Runs as | Context | Notes | Price |
|---|---|---|---|---|---|---|---|---|
| Apple M5 Ultra · 256 GB | Runs great | est. 61.9 tok/s49.5–74.3calibrated estimate ±20% | Q4_K_M | 68.6 / 179.2 GB | Unified memory | up to 128k | — | — |
| Apple M5 Max (40-core GPU) · 128 GB | Runs great | est. 53.6 tok/s42.9–64.3calibrated estimate ±20% | Q4_K_M | 68.6 / 89.6 GB | Unified memory | up to 128k | — | — |
| Apple M4 Max (40-core GPU) · 128 GB | Runs great | est. 49.1 tok/s39.2–58.9calibrated estimate ±20% | Q4_K_M | 68.6 / 89.6 GB | Unified memory | up to 64k | — | — |
| Apple M3 Ultra · 256 GB | Runs great | est. 48.1 tok/s38.5–57.7calibrated estimate ±20% | Q4_K_M | 68.6 / 179.2 GB | Unified memory | up to 64k | — | — |
| Apple M2 Ultra · 128 GB | Runs great | est. 47.3 tok/s37.9–56.8calibrated estimate ±20% | Q4_K_M | 68.6 / 89.6 GB | Unified memory | up to 64k | — | — |
| NVIDIA DGX Spark · 128 GB | Runs well | est. 28.4 tok/s22.7–34.1calibrated estimate ±20% | Q4_K_M | 68.6 / 116.9 GB | Unified memory | up to 128k | — | $3,999 launch MSRP (128 GB) |
| Ryzen AI Max+ 395 (Strix Halo) · 128 GB | Runs well | est. 26.4 tok/s21.1–31.7calibrated estimate ±20% | Q4_K_M | 68.6 / 89.6 GB | Unified memory | up to 128k | — | $1,999 launch MSRP (128 GB) |
| DDR5-6000 dual-channel CPU · 96 GB | Runs slowly | est. 8.2 tok/s6.6–9.9calibrated estimate ±20% | Q4_K_M | 68.1 GB RAM | CPU only | up to 128k | — | — |
| DDR5-5600 dual-channel CPU · 96 GB | Runs slowly | est. 7.7 tok/s6.2–9.2calibrated estimate ±20% | Q4_K_M | 68.1 GB RAM | CPU only | up to 128k | — | — |
| Apple M4 · 32 GB | Won't run | — | Q4_K_M | needs 68.6 GB | — | — |
| — |
| Apple M4 Max (32-core GPU) · 36 GB | Won't run | — | Q4_K_M | needs 68.6 GB | — | — |
| — |
| Apple M4 Pro · 64 GB | Won't run | — | Q4_K_M | needs 68.6 GB | — | — |
| — |
| Apple M5 · 32 GB | Won't run | — | Q4_K_M | needs 68.6 GB | — | — |
| — |
| Apple M5 Max (32-core GPU) · 36 GB | Won't run | — | Q4_K_M | needs 68.6 GB | — | — |
| — |
| Apple M5 Pro · 64 GB | Won't run | — | Q4_K_M | needs 68.6 GB | — | — |
| — |
| Apple M6 · 32 GB | Won't run | — | Q4_K_M | needs 68.6 GB | — | — |
| — |
| Intel Arc B580 | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $290 street (as of 2026-08-09) |
| DDR4-3200 dual-channel CPU · 64 GB | Won't run | — | Q4_K_M | needs 68.1 GB | — | — |
| — |
| GeForce GTX 1080 Ti | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $699 launch MSRP |
| GeForce RTX 2080 Ti | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $999 launch MSRP |
| GeForce RTX 3050 8GB | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $249 launch MSRP |
| GeForce RTX 3060 12GB | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $250 street (as of 2026-08-09) |
| GeForce RTX 3070 | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $499 launch MSRP |
| GeForce RTX 3080 10GB | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $699 launch MSRP |
| GeForce RTX 3080 12GB | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $799 launch MSRP |
| GeForce RTX 3090 | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $1,050 street (as of 2026-08-09) |
| GeForce RTX 3090 Ti | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $1,999 launch MSRP |
| GeForce RTX 4060 | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $299 launch MSRP |
| GeForce RTX 4060 Laptop | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| — |
| GeForce RTX 4060 Ti 16GB | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $499 launch MSRP |
| GeForce RTX 4060 Ti 8GB | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $399 launch MSRP |
| GeForce RTX 4070 | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $599 launch MSRP |
| GeForce RTX 4070 Laptop | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| — |
| GeForce RTX 4070 Super | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $599 launch MSRP |
| GeForce RTX 4070 Ti Super | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $799 launch MSRP |
| GeForce RTX 4080 | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $1,199 launch MSRP |
| GeForce RTX 4080 Laptop | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| — |
| GeForce RTX 4080 Super | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $999 launch MSRP |
| GeForce RTX 4090 | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $2,755 street (as of 2026-08-09) |
| GeForce RTX 4090 Laptop | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| — |
| GeForce RTX 5060 | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $339 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 16GB | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $569 street (as of 2026-08-09) |
| GeForce RTX 5060 Ti 8GB | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $429 street (as of 2026-08-09) |
| GeForce RTX 5070 | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $629 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $949 street (as of 2026-08-09) |
| GeForce RTX 5070 Ti Laptop | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| — |
| GeForce RTX 5080 | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $1,256 street (as of 2026-08-09) |
| GeForce RTX 5080 Laptop | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| — |
| GeForce RTX 5090 | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $4,200 street (as of 2026-08-09) |
| GeForce RTX 5090 Laptop | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| — |
| Radeon RX 7800 XT | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $499 launch MSRP |
| Radeon RX 7900 XT | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $899 launch MSRP |
| Radeon RX 7900 XTX | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $999 launch MSRP |
| Radeon RX 9060 XT 16GB | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $449 street (as of 2026-08-09) |
| Radeon RX 9070 | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $639 street (as of 2026-08-09) |
| Radeon RX 9070 XT | Won't run | — | Q4_K_M | needs 68.5 GB | — | — |
| $689 street (as of 2026-08-09) |
Models with a thinking mode spend extra tokens thinking, so their speed thresholds are 1.5× stricter (30 / 12 / 3 tok/s). With thinking turned off, a model may do one grade better.
Cheapest GPUs that run it
No GPU with a current street price reaches Runs great or Runs well at Q4_K_M. The table above lists Macs, unified-memory PCs and CPU setups.
Measured results for Laguna S 2.1
No public measurements for this model yet.
Frequently asked questions
How much VRAM does Laguna S 2.1 need?
At Q4_K_M the file is 67.66 GB; with 8k context a graphics card needs about 68.5 GB (weights 67.48 GB, KV cache 0.4 GB, compute buffer 0.6 GB). Part of the file stays off the graphics card: llama.cpp keeps the input embedding table in system RAM. A Mac counts the whole file, so it needs a little more.
What is the cheapest GPU that runs Laguna S 2.1 well?
No GPU with a current street price reaches Runs great or Runs well at Q4_K_M. The best tracked option is Apple M5 Ultra · 256 GB: Runs great.
Can Laguna S 2.1 run on an 8 GB, 16 GB or 24 GB GPU?
At Q4_K_M with 8k context: GeForce RTX 4060 — Won't run; GeForce RTX 5060 Ti 16GB — Won't run; GeForce RTX 3090 — Won't run.
Speeds are estimates from memory bandwidth, calibrated against public benchmarks, and each one comes with an error band and a confidence label. Real results vary with drivers, backend, context length and thermals.