TurboLaguna-XS
Canonical artifact: Laguna-XS-2.1-TQ3_4S
TurboLaguna-XS is the TurboQuant GGUF build of Poolside's Laguna XS 2.1 — a sigmoid-routed mixture-of-experts coding model with 256 experts per layer, a shared expert, QK-norm, and hybrid YaRN/sliding-window RoPE.
The exact file and runtime artifact name is:
Laguna-XS-2.1-TQ3_4S.gguf
Required Runtime
This model uses the custom TQ3_4S tensor type. Stock llama.cpp builds
cannot load it. You must use the TurboQuant runtime fork:
This is a standard (non-MTP) model — no draft-MTP flags are needed.
Parent Model
Upstream parent: poolside/Laguna-XS-2.1-GGUF
Source quant: Laguna-XS-2.1-BF16.gguf (63.8 GB, 16.01 bpw)
Format conversion and TurboQuant packaging: turbo-tan/llama.cpp-tq3
Files
File Size Notes Laguna-XS-2.1-TQ3_4S.gguf16 GB (4.05 bpw) Main model — 678 tensors, 40 layers × 256 routed experts thumbnail.png— Model card image benchmark.png— Benchmark summary
Quantization Recipe
Quantized from the official BF16 GGUF using the standard TQ3_4S recipe:
1 ./build/bin/llama-quantize --allow-requantize \
2 --output-tensor-type q6_K \
3 --token-embedding-type q6_K \
4 Laguna-XS-2.1-BF16.gguf \
5 Laguna-XS-2.1-TQ3_4S.gguf \
6 TQ3_4S
Tensor policy:
Routed experts, attention projections, shared experts → tq3_4s (4.0 bpw)
Token embeddings, output head → q6_K
Norms, gates, biases → f32 (untouched)
Result: 63.8 GB → 16 GB (3.98× compression), 42% smaller than Poolside's own Q4_K_M (20 GB).
Recommended Runtime
1 ./build/bin/llama-server \
2 -m Laguna-XS-2.1-TQ3_4S.gguf \
3 --host 127.0 .0.1 --port 8080 \
4 -c 8192 -np 1 -ngl 99 -fa on \
5 --reasoning off --jinja
Build note:
-fa on is the runtime flash-attention flag, not the CMake GGML_CUDA_FA_ALL_QUANTS build flag.
GPU Memory Profiles
GPU memory Suggested context KV cache Notes 16 GiB 4096-ctk q4_0 -ctv tq3_0Tight fit — keep context small 24 GiB 8192 to 32768-ctk q8_0 -ctv tq3_0Validated desktop profile 128 GiB GB10 65536+-ctk q4_0 -ctv tq3_0Full headroom for long context
Tested Hardware
NVIDIA RTX 3090 24 GB — primary validation platformllama.cpp-tq3 fork, branch feat/laguna-arch (Laguna arch from upstream ggml-org/llama.cpp#25165 )
Benchmarks
All scores: greedy decoding, reasoning off, -ngl 99 -fa on, RTX 3090.
Benchmark Score tok/s HumanEval (base) 0.805 196 HumanEval+ (extra tests) 0.762 196 MBPP (base) 0.833 199 MBPP+ (extra tests) 0.720 199 Hard86 (20 tasks / 86 assertions) 64.0% (55/86)202 BenchLoop coding 100.0 (12/12)— BenchLoop overall 73.7 — BenchLoop speed 96.4 (9/9)—
Comparison (all TQ3_4S, same RTX 3090)
Model HE+ MBPP+ Hard86 Coding tok/s Size Laguna XS 2.1 0.762 0.720 64.0% 100.0 196 16 GB Qwen3.5 9B 0.671 0.563 44.2% 79.2 134 4.5 GB Qwen3.6 27B MTP 0.927 0.878 — 100.0 42–54 12.9 GB
Laguna XS is a coding specialist: perfect BenchLoop coding (same as the 27B), +19.8pp Hard86 over the 9B, at 3.6–4.6× the 27B's decode speed.
Validation
llama-simple-chat coherence smoke: PASS
llama-server --reasoning off strict smoke: PASS (content = "ok")
llama-bench pp2048: 745 tok/s
llama-bench tg128: 196 tok/s
evalplus HE/HE+/MBPP/MBPP+: scored (see above)
hard86: 55/86
benchloop v0.2.3: overall 73.7License
Parent model: OpenMDW-1.1 (Poolside)
Runtime: turbo-tan/llama.cpp-tq3 (MIT)
