Laguna S · 2.1

Poolside's Laguna S 2.1, a coding assistant model. Runs across four Arc Pro B70 cards with a draft model speeding up generation; measured as a coding-first deployment.

125.46tok/s
measured
≈ 94 words a secondlaguna-s-2.1-int4-4bbfc28 · INT4 target + INT4 DFlash draft / BF16 KV · vLLM XPU 1a7f61feffbc61b21b73f812d231c7426386ccdc · 4× B70 · B70-verified originating-host replay
Laguna S 2.1 INT4 · target/verifier checkpoint
B70 fit
High
Quality evidence
Strong deployment evidence
Measured results
2

Packets and recipes

The deployment variants of this family, at every maturity.

What has been classified

Dense scorecards summarize every declared combination; measured slices retain exact evidence links.

long context · screened

Pinned INT4 target and DFlash draft · BF16 KV · q12 verifier · one request · cache zero. TP4 points are bounded retrieval-screen medians, not exact-output measurements; TP1, TP2, and TP3 were not run. Fixed: revision=laguna-s-2.1-int4-4bbfc28 · variant=INT4 target + INT4 DFlash draft / BF16 KV · runtime=vLLM XPU 1a7f61feffbc61b21b73f812d231c7426386ccdc + XPU kernels 99886d783372e621941228250091dc8ebdc1595d · profile_id=laguna-q12-long-context-gpu080-composed · ep=4 · speculative_method=DFlash · draft_depth=11 · verifier_width=12 · kv=bfloat16 · configured_max_context_tokens=32768 · output_tokens=128.

  • ◇ Speed check only4 cards, 1K TP4·1K — Two-row median after excluding the first-live capture/JIT row; retrieval and q1 output equality passed; DFlash acceptance 23.56%.D153.6 · P5,172 · T201.77 · AR0.24evidence
  • ◇ Speed check only4 cards, 4K TP4·4K — Three-row median; retrieval passed but q1 output equality failed; DFlash acceptance 11.36%.D80.24 · P7,332 · T564.3 · AR0.11evidence
  • ◇ Speed check only4 cards, 8K TP4·8K — Three-row median; retrieval passed but q1 output equality failed; DFlash acceptance 2.34%.D46.81 · P4,130 · T1,993 · AR0.02evidence
  • ◇ Speed check only4 cards, 16K TP4·16K — Three-row median; retrieval passed but q1 output equality failed; DFlash acceptance 0.86%.D40.41 · P5,111 · T3,228 · AR0.01evidence
  • ◇ Speed check only4 cards, 24K TP4·24K — Three-row median; retrieval passed but q1 output equality failed; DFlash acceptance 0.85%.D39.78 · P5,053 · T4,883 · AR0.01evidence
  • ◇ Speed check only4 cards, 32,640 TP4·32,640 — Three-row median; retrieval passed but q1 output equality failed; DFlash acceptance 0.47%.D39.59 · P7,345 · T4,478 · AR0evidence

Codes in the rows: D = decode tok/s · P = prefill tok/s · T = ms to first token · AR = share of drafted tokens accepted · A = combined tok/s.

18 untested combinations
TP1·1KTP2·1KTP3·1KTP1·4KTP2·4KTP3·4KTP1·8KTP2·8KTP3·8KTP1·16KTP2·16KTP3·16KTP1·24KTP2·24KTP3·24KTP1·32,640TP2·32,640TP3·32,640
Full matrix and exact selectors

Measured results

Every number links to its proof.

family data

How the record improved

Same pinned INT4 target and DFlash draft, TP4+EP4, DFlash11, width-12 verifier, BF16 KV; runtime revisions differ and values use conventional 99-interval accounting

qualified records · qualified record generation 1101.94tok/sDecode5,759msTTFTlab measurement; quality scope in evidence · evidence
qualified records · qualified record generation 2125.46tok/sDecode5,954msTTFTlab measurement; quality scope in evidence · evidence
qualified records
evidence 1 · evidence 2

Draft-model efficiency (earlier runs)

The sealed 2026-07-26 packet is the only stored family measurement with aggregate acceptance and emitted tokens per draft cycle

historical sealed packet · draft tokens 110.27ratioDraft acceptance3.95tokensEffective tokens / verifylab measurement; quality scope in evidence · evidence
historical sealed packet
evidence 1
Fine print

single pinned target/draft pair with revision-specific runtime and native artifacts. Measurements, artifact hashes, outputs, quality decisions, and speed stay pinned to their exact recorded identity.

4 combinations the lab has stopped pursuing: No qualified performance or quality profile is stored for this exact target/draft pair outside the four-card TP4+EP4 topology. evidence A bounded TP4 retrieval screen covers 1K through 32,640, but every 4K-and-longer output diverged from the target-only q1 oracle; no promotion-grade exact context curve is stored. evidence The current record remains tied to exact originating-host runtime and native artifacts; a portable runtime rebuild is not stored. evidence No non-originating-host replay has completed the full record gate. evidence Exact selectors are in the family data.

Many people at once Not measured

Multi-user (aggregate) throughput has not been measured for this family. The lab’s one measured sweep so far is in the multi-user report; the projection block below includes a projected users curve where a projection exists.

How much faster could this get? Projected — not measured

The ML Bottleneck physics engine projects a tuned-run target and the physical ceiling for the headline setup (laguna-s-2.1-int4- · INT4 target + INT4 DFlash draft / BF16 KV · vLLM XPU · 4× B70). The grade is optimization headroom against the tuned-run target, not model quality.