Runs on ≤24 GB · Hugging Face ↗
Not independently scored by Artificial Analysis
Poolside's first open-weight coder — 33B total / ~3B active MoE, Apache-2.0, built for agentic long-horizon coding. Reportedly 68.2% SWE-bench Verified and beating dense models 10x its size; the local-runnable member of the Laguna family (S 2.1 / M.1 are data-centre). Custom `LagunaForCausalLM` arch.
BigCodeBench-Hard pass@1 29% (43/148), via official protocol · vLLM · one request at a time · a shared cluster GPU · mean of 3 runs, range 0.0 pp. The brutal counterpart to HumanEval — where HumanEval saturates near the top, BCB-Hard spreads the field, so this is the number that actually separates coding ability. served artifact not verified; different runtime; 1 of 148 answers hit the token limit (effective ceiling 99%)
Our own runs on this model. Each number carries how many problems it is over and how many times we ran it — these are not comparable with each other, and none of them is on the same scale as the third-party indices on the leaderboard.
| test | score | over | conditions |
|---|---|---|---|
| BigCodeBench-Hard | 29.0% | n=148 · 3 run(s) | official protocol · vLLM · one request at a time · a shared cluster GPU · mean of 3 runs, range 0.0 pp |
Real GGUF file sizes = weight VRAM. Add the KV cache for your context (≈2 GB at 32K, fp16). Read from the GGUF header, but this architecture has never been checked against llama.cpp — treat it as an estimate.
| Quantization | Size |
|---|---|
| IQ2_XXS | 9.4 GB |
| IQ2_XS | 10.4 GB |
| IQ2_S | 10.6 GB |
| IQ2_M | 11.6 GB |
| Q2_K | 12.2 GB |
| Q2_K_L | 12.4 GB |
| IQ3_XXS | 14.3 GB |
| Q3_K_S | 14.9 GB |
| IQ3_XS | 15.6 GB |
| Q3_K_M | 15.6 GB |
| Q3_K_L | 16.1 GB |
| IQ3_M | 16.3 GB |
| Q3_K_XL | 16.3 GB |
| IQ4_XS | 18.2 GB |
| Q4_0 | 19.2 GB |
| IQ4_NL | 19.2 GB |
| Q4_K_S | 19.8 GB |
| Q4_K_M | 20.5 GB |
| Q4_K_L | 20.7 GB |
| Q4_1 | 21.2 GB |
| Q5_K_S | 23.2 GB |
| Q5_K_M | 24.0 GB |
| Q5_K_L | 24.1 GB |
| Q6_K | 29.0 GB |
| Q6_K_L | 29.1 GB |
| Q8_0 | 35.6 GB |
| BF16 | 66.9 GB |
~20 GB at Q4 — a 24 GB+ card or the 32 GB tier. Also on OpenRouter (laguna-xs-2.1:free) and opencode Zen's free set, so you can try the family for $0 before committing local VRAM.