← All releases
Release benchmarks

Antfly 0.3

Antfly combines full-text, vector and graph search with document extraction and local model inference. This page measures retrieval quality, query latency, memory use and inference on CUDA and Metal, with the tested configurations and versions in each section.

01

Inference

Antfly runs extraction, embedding, decision, generative, speech and OCR models on its own GPU kernels. These plots compare speed and peak memory on CUDA and Metal with each model’s reference runtime, for models that Antfly Cloud also hosts.

Antfly inference · CUDA

NVIDIA L4 GPU. Same weights on both sides; each mark is one workload. Measured on Antfly v0.3.1.

GLiNER2.5 base (vs Fastino gliner2 2.1.0): Speed 7/7, memory 7/7 complete. speed sentence, Antfly 2.90× faster; paragraph, Antfly 1.92× faster; 350-word page, Upstream 1.13× faster; Wikipedia paragraph, Antfly 1.72× faster; entities + classes + relations, Antfly 1.84× faster; 8 paragraphs per request, Upstream 1.12× faster; 32 paragraphs per request, Antfly 1.04× faster. memory sentence, Antfly 1.72× smaller memory footprint (Antfly 1.77 GB vs upstream 3.06 GB); paragraph, Antfly 1.75× smaller memory footprint (Antfly 1.77 GB vs upstream 3.09 GB); 350-word page, Antfly 1.75× smaller memory footprint (Antfly 1.77 GB vs upstream 3.10 GB); Wikipedia paragraph, Antfly 1.53× smaller memory footprint (Antfly 2.04 GB vs upstream 3.11 GB); entities + classes + relations, Antfly 1.81× smaller memory footprint (Antfly 1.77 GB vs upstream 3.20 GB); 8 paragraphs per request, Antfly 1.96× smaller memory footprint (Antfly 1.86 GB vs upstream 3.64 GB); 32 paragraphs per request, Antfly 2.65× smaller memory footprint (Antfly 1.86 GB vs upstream 4.93 GB). EmbeddingGemma 2 (vs sentence-transformers 6.2.0): Speed 7/7, memory 7/7 complete. speed sentence, Antfly 5.48× faster; 32 sentences per request, Upstream 2.51× faster; paragraph, Antfly 3.70× faster; 32 paragraphs per request, Upstream 1.39× faster; 8 pages per request, Upstream 1.56× faster; ~2K-token document, Upstream 2.50× faster; ~7K-token document, Upstream 4.59× faster. memory sentence, Antfly 1.17× smaller memory footprint (Antfly 3.70 GB vs upstream 4.34 GB); 32 sentences per request, Antfly 1.33× smaller memory footprint (Antfly 3.69 GB vs upstream 4.91 GB); paragraph, Antfly 1.20× smaller memory footprint (Antfly 3.69 GB vs upstream 4.42 GB); 32 paragraphs per request, Antfly 1.44× smaller memory footprint (Antfly 3.70 GB vs upstream 5.34 GB); 8 pages per request, Antfly 1.44× smaller memory footprint (Antfly 3.68 GB vs upstream 5.32 GB); ~2K-token document, Antfly 1.21× smaller memory footprint (Antfly 3.69 GB vs upstream 4.44 GB); ~7K-token document, Antfly 1.67× smaller memory footprint (Antfly 3.68 GB vs upstream 6.13 GB). GLiNER2.5-Decide (vs Fastino gliner2 2.1.0): Speed 3/3, memory 3/3 complete. speed 1 review per request, Antfly 2.44× faster; 8 per request, Antfly 1.15× faster; 32 per request, Antfly 1.10× faster. memory 1 review per request, Antfly 1.21× smaller memory footprint (Antfly 3.96 GB vs upstream 4.80 GB); 8 per request, Antfly 1.26× smaller memory footprint (Antfly 3.96 GB vs upstream 5.00 GB); 32 per request, Antfly 1.45× smaller memory footprint (Antfly 3.96 GB vs upstream 5.73 GB). Gemma 4 E4B (vs llama.cpp b10809): Speed 5/5, memory 5/5 complete. speed short prompt, 256 tokens out, Antfly 1.04× faster; 350-word page, 128 out, Antfly 1.06× faster; ~2K-token prompt, 64 out, Antfly 1.12× faster; image, 64 out, Antfly 1.07× faster; 5–15 s audio, 64 out, Antfly 1.05× faster. memory short prompt, 256 tokens out, Antfly 1.22× smaller memory footprint (Antfly 7.07 GB vs upstream 8.60 GB); 350-word page, 128 out, Antfly 1.06× smaller memory footprint (Antfly 8.11 GB vs upstream 8.60 GB); ~2K-token prompt, 64 out, Upstream 1.00× smaller memory footprint (Antfly 8.61 GB vs upstream 8.60 GB); image, 64 out, Antfly 1.06× smaller memory footprint (Antfly 8.11 GB vs upstream 8.62 GB); 5–15 s audio, 64 out, Antfly 1.07× smaller memory footprint (Antfly 8.06 GB vs upstream 8.60 GB). Same prompt token count on all 46 inputs; generated text matches llama.cpp on none. Not identical outputs.. Whisper small (vs Transformers 5.23.0): Speed 3/3, memory 3/3 complete. speed 5.9 s clip, Antfly 2.91× faster; 15.1 s clip, Antfly 3.54× faster; 29.4 s clip, Antfly 4.11× faster. memory 5.9 s clip, Antfly 1.56× smaller memory footprint (Antfly 2.13 GB vs upstream 3.33 GB); 15.1 s clip, Antfly 1.55× smaller memory footprint (Antfly 2.19 GB vs upstream 3.39 GB); 29.4 s clip, Antfly 1.58× smaller memory footprint (Antfly 2.14 GB vs upstream 3.39 GB). LightOnOCR-3 0.8B (vs Transformers 5.23.0): Speed 1/1, memory 1/1 complete. speed one page, Antfly 2.60× faster. memory one page, Antfly 1.24× smaller memory footprint (Antfly 3.82 GB vs upstream 4.73 GB)

  • Speed: upstream time ÷ Antfly time
  • Peak memory: upstream ÷ Antfly
  • Hollow: upstream better on that workload

Speed by model · CUDA

Model
GLiNER2.5 base
Compared against
Fastino gliner2 2.1.0
Typical workload
1.72× faster
Range
1.13× slower to 2.90× faster
Model
EmbeddingGemma 2
Compared against
sentence-transformers 6.2.0
Typical workload
1.56× slower
Range
4.59× slower to 5.48× faster
Model
GLiNER2.5-Decide
Compared against
Fastino gliner2 2.1.0
Typical workload
1.15× faster
Range
1.10× to 2.44× faster
Model
Gemma 4 E4B
Compared against
llama.cpp b10809
Typical workload
1.06× faster
Range
1.04× to 1.12× faster
Model
Whisper small
Compared against
Transformers 5.23.0
Typical workload
3.54× faster
Range
2.91× to 4.11× faster
Model
LightOnOCR-3 0.8B
Compared against
Transformers 5.23.0
Typical workload
2.60× faster
Range
One workload
Details

Antfly is slower on CUDA for EmbeddingGemma 2 with batches and long documents (1.4–4.6×); on Metal for Whisper small (4.5–5.4×), GLiNER2.5-Decide (2.5–3.1×), EmbeddingGemma 2 (up to 2.2×), Gemma 4 E4B on image input (1.3×) and GLiNER2.5 base on the 350-word page (1.2×). On Metal it uses 1.1–1.5× more memory for Gemma 4 E4B, Whisper small and batched GLiNER2.5-Decide.

These are selected workloads.

Tested versions

Antfly
v0.3.1
Fastino gliner2
2.1.0
sentence-transformers
6.2.0 · PyTorch 2.15.0 · CUDA and MPS · BF16
llama.cpp
b10809 · llama-server · CUDA and Metal · same Q4_0 GGUF files
Hugging Face Transformers
5.23.0 · PyTorch 2.15.0 · CUDA and MPS

Do the outputs match upstream? Same on CUDA and Metal unless noted

Model
GLiNER2.5 base
Agreement with upstream
1,344/1,344 paired outputs identical.
Model
EmbeddingGemma 2
Agreement with upstream
Cosine ≥0.9997 on every timed vector. SciFact, 24 queries: recall@1 0.93 vs 0.89 on CUDA, 0.89 vs 0.89 on Metal.
Model
GLiNER2.5-Decide
Agreement with upstream
960/960 paired outputs identical.
Model
Gemma 4 E4B
Agreement with upstream
Generated text identical on 0/46 inputs; audio word error rate 5.3% vs llama.cpp 4.8%. GSM8K: 5/12 correct vs 4/12. ARC-Challenge: 6/12 vs 3/12.
Model
Whisper small
Agreement with upstream
42 of 568 words wrong on 32 LibriSpeech clips; Transformers 43.
Model
LightOnOCR-3 0.8B
Agreement with upstream
Both read the timed page, 22 words, without error; the text is identical.

Methodology

  • Measured November 17, 2026 (UTC) on Antfly v0.3.1. CUDA: NVIDIA L4. Metal: Apple M4 Max, 36 GiB.
  • Both sides get identical input bytes and model checkpoints. Timing is the median of three paired, alternating runs after warm-up. Antfly timings include local HTTP and JSON overhead; references run in-process, except Gemma 4, which uses HTTP on both sides.
  • Memory is the median peak of three fresh processes. CUDA: host plus GPU memory. Metal: the macOS memory footprint plus the model file held in RAM, counted in full on both sides. Part of that file may already be in the footprint, so the real figures can be lower.
  • LightOnOCR: Transformers ran with generation caching on (use_cache=True); the checkpoint’s own setting leaves it off. Antfly’s time excludes the caller’s image encoding; the Transformers time includes its image preparation.
  • Precision: both sides run the same checkpoint and differ in three places. Whisper: Transformers FP32; Antfly uses FP16 operands with FP32 accumulation, for weights on CUDA and encoder attention on Metal. LightOnOCR: Transformers computes in BF16, Antfly mostly in FP32. GLiNER2.5-Decide on Metal: Antfly holds the encoder weights in FP16.
Benchmark harness
02

Retrieval quality

STaRK-Prime measures document retrieval for specific biomedical questions. Quality is measured by Recall@20: the fraction of expected answers returned in the first 20 results, averaged across queries. Retrieval method matters: Antfly’s hybrid search over relation-expanded text reaches 49.34%, versus 36.00% for dense retrieval.

Benchmark definition

STaRK-Prime · hybrid over relation-expanded text

Recall@20 across 2,801 questions. Higher is better.

Recall@20 across 2,801 questions. Higher is better.. Antfly: Antfly, 49.34%. Neo4j: Neo4j, 48.40%. Weaviate: Weaviate, 48.19%. Milvus: Milvus, 46.65%. Elasticsearch: Elasticsearch, 43.91%. Postgres + pgvector: Postgres + pgvector, 30.43%

  • Antfly 0.3
  • Other systems
Details

Tested versions

Antfly
v0.3.0
Chroma
1.0.0
Elasticsearch
9.4.1
Neo4j
5.26.29
Postgres + pgvector
0.8.5 on PostgreSQL 16.14
Weaviate
1.38.2
Milvus
3.0.0
Quickwit
0.9.0

STaRK-Prime Recall@20 · every database and method

STaRK-Prime Recall@20 · every database and method
DatabaseDense · official vectorsLexical · default textHybrid · default textLexical · relation-expandedHybrid · relation-expanded
Antfly36.00%33.47%40.41%45.32%49.34%
Neo4j34.42%31.64%39.21%43.06%48.40%
Weaviate35.34%31.77%39.24%43.80%48.19%
Milvus32.61%31.76%37.51%43.49%46.65%
Elasticsearch35.78%31.58%32.66%43.06%43.91%
QuickwitUnsupported30.85%Unsupported42.65%Unsupported
Postgres + pgvector35.55%3.07%29.35%3.60%30.43%
Chroma34.94%UnsupportedUnsupportedUnsupportedUnsupported

Methodology

  • Apple M4 Max, Docker Desktop Linux arm64 VM (10 CPUs, 19.5 GiB), measured Nov 13, 2026.
  • 129,375 candidate documents and 2,801 questions; every question counts in every score. All systems use the official text-embedding-ada-002 vectors. “Relation-expanded text” writes each record’s relationships into its text before indexing. Hybrid search merges lexical and vector results with reciprocal rank fusion.
  • Antfly’s vector search ran at maximum search effort, which scans every vector: its dense score equals exact search, at 508–595 ms per dense or hybrid query. The other databases used approximate HNSW search with ef=200.
03

Full-text search

799 MIRACL English queries · 1 client · 250K–3M passages.

  • Antfly v0.3
  • Elasticsearch
  • Quickwit

Query p95 (ms)

1 client · lower is better

Query p951 client · lower is better. Antfly: 250K, 3.79 [3.72–3.85] ms, observed range 3.7160817998483244–3.8468551999699123; 1M, 10.57 [10.35–10.74] ms, observed range 10.347395600001617–10.743218800325845; 2M, 19.81 [19.63–19.94] ms, observed range 19.625205899683326–19.939437400125822; 3M, 27.12 [26.51–28.94] ms, observed range 26.50663210015409–28.938529799779623. Elasticsearch: 250K, 3.28 [3.28–3.44] ms, observed range 3.277086900925496–3.4403429999997566; 1M, 4.75 [4.75–4.88] ms, observed range 4.748033500436577–4.883648599866318; 2M, 6.49 [6.13–6.60] ms, observed range 6.127399899742157–6.6038590002790425; 3M, 9.43 [9.35–9.51] ms, observed range 9.352011599821706–9.512670099775276. Quickwit: 250K, 24.38 [24.37–24.43] ms, observed range 24.36941489995661–24.428795100061507; 1M, 25.36 [25.29–25.39] ms, observed range 25.292908599112707–25.391484700026012; 2M, 25.70 [25.53–25.73] ms, observed range 25.52749379965462–25.727922099304124; 3M, 25.93 [25.89–26.02] ms, observed range 25.889383499725227–26.021289200343745010203040250K1M2M3MPassagesAntfly v0.3 · 250K · 3.79 [3.72–3.85] ms · observed range 3.7160817998483244–3.8468551999699123Antfly v0.3 · 1M · 10.57 [10.35–10.74] ms · observed range 10.347395600001617–10.743218800325845Antfly v0.3 · 2M · 19.81 [19.63–19.94] ms · observed range 19.625205899683326–19.939437400125822Antfly v0.3 · 3M · 27.12 [26.51–28.94] ms · observed range 26.50663210015409–28.938529799779623Elasticsearch · 250K · 3.28 [3.28–3.44] ms · observed range 3.277086900925496–3.4403429999997566Elasticsearch · 1M · 4.75 [4.75–4.88] ms · observed range 4.748033500436577–4.883648599866318Elasticsearch · 2M · 6.49 [6.13–6.60] ms · observed range 6.127399899742157–6.6038590002790425Elasticsearch · 3M · 9.43 [9.35–9.51] ms · observed range 9.352011599821706–9.512670099775276Quickwit · 250K · 24.38 [24.37–24.43] ms · observed range 24.36941489995661–24.428795100061507Quickwit · 1M · 25.36 [25.29–25.39] ms · observed range 25.292908599112707–25.391484700026012Quickwit · 2M · 25.70 [25.53–25.73] ms · observed range 25.52749379965462–25.727922099304124Quickwit · 3M · 25.93 [25.89–26.02] ms · observed range 25.889383499725227–26.02128920034374527.129.4325.93

Peak memory demand (MB)

anon + shmem · lower is better

Peak memory demandanon + shmem · lower is better. Antfly: 250K, 927.6 [916.6–954.3] MB, observed range 916.6069759999999–954.298368; 1M, 1,882.0 [1,872.2–2,035.3] MB, observed range 1872.2365439999999–2035.28192; 2M, 2,755.6 [2,724.1–2,832.6] MB, observed range 2724.0611839999997–2832.6420479999997; 3M, 3,530.8 [3,433.5–3,626.3] MB, observed range 3433.463808–3626.319872. Elasticsearch: 250K, 1,814.3 [1,801.2–1,940.3] MB, observed range 1801.248768–1940.2670079999998; 1M, 1,941.1 [1,916.3–1,983.6] MB, observed range 1916.2767359999998–1983.602688; 2M, 1,917.4 [1,878.8–1,934.4] MB, observed range 1878.8229119999999–1934.442496; 3M, 1,973.7 [1,908.1–2,003.4] MB, observed range 1908.08064–2003.378176. Quickwit: 250K, 427.2 [409.3–442.6] MB, observed range 409.346048–442.5728; 1M, 978.2 [894.5–996.8] MB, observed range 894.476288–996.810752; 2M, 1,323.3 [1,322.7–1,399.0] MB, observed range 1322.749952–1398.960128; 3M, 1,569.8 [1,559.9–1,662.1] MB, observed range 1559.887872–1662.066687999999901,0002,0003,0004,000250K1M2M3MPassagesAntfly v0.3 · 250K · 927.6 [916.6–954.3] MB · observed range 916.6069759999999–954.298368Antfly v0.3 · 1M · 1,882.0 [1,872.2–2,035.3] MB · observed range 1872.2365439999999–2035.28192Antfly v0.3 · 2M · 2,755.6 [2,724.1–2,832.6] MB · observed range 2724.0611839999997–2832.6420479999997Antfly v0.3 · 3M · 3,530.8 [3,433.5–3,626.3] MB · observed range 3433.463808–3626.319872Elasticsearch · 250K · 1,814.3 [1,801.2–1,940.3] MB · observed range 1801.248768–1940.2670079999998Elasticsearch · 1M · 1,941.1 [1,916.3–1,983.6] MB · observed range 1916.2767359999998–1983.602688Elasticsearch · 2M · 1,917.4 [1,878.8–1,934.4] MB · observed range 1878.8229119999999–1934.442496Elasticsearch · 3M · 1,973.7 [1,908.1–2,003.4] MB · observed range 1908.08064–2003.378176Quickwit · 250K · 427.2 [409.3–442.6] MB · observed range 409.346048–442.5728Quickwit · 1M · 978.2 [894.5–996.8] MB · observed range 894.476288–996.810752Quickwit · 2M · 1,323.3 [1,322.7–1,399.0] MB · observed range 1322.749952–1398.960128Quickwit · 3M · 1,569.8 [1,559.9–1,662.1] MB · observed range 1559.887872–1662.06668799999993,5311,9741,570
Details

Figures are medians of three fresh indexes per engine and corpus size (storage is the mean); whiskers show the min–max. Peak memory excludes reclaimable file cache.

Antfly Recall@100 falls from 0.917 at 1M to 0.813 at 2M and 0.751 at 3M, and varies across fresh indexes (0.789–0.813 at 2M; 0.725–0.755 at 3M). Self-text checks missed 1–4 sampled relevant passages in Antfly and none in the other two engines. The cause is unresolved.

Tested versions

Antfly
v0.3.0
Elasticsearch
9.5.2
Quickwit
0.9.0

All engines and corpus sizes

Engine
Antfly
Passages
250,000
p95 (ms)
3.79
nDCG@10
0.578
Recall@100
0.940
Peak memory (MB)
927.6
Storage (MB)
193.9
Engine
Elasticsearch
Passages
250,000
p95 (ms)
3.28
nDCG@10
0.552
Recall@100
0.930
Peak memory (MB)
1,814.3
Storage (MB)
123.3
Engine
Quickwit
Passages
250,000
p95 (ms)
24.38
nDCG@10
0.557
Recall@100
0.942
Peak memory (MB)
427.2
Storage (MB)
284.9
Engine
Antfly
Passages
1,000,000
p95 (ms)
10.57
nDCG@10
0.531
Recall@100
0.917
Peak memory (MB)
1,882.0
Storage (MB)
746.0
Engine
Elasticsearch
Passages
1,000,000
p95 (ms)
4.75
nDCG@10
0.493
Recall@100
0.892
Peak memory (MB)
1,941.1
Storage (MB)
477.4
Engine
Quickwit
Passages
1,000,000
p95 (ms)
25.36
nDCG@10
0.499
Recall@100
0.907
Peak memory (MB)
978.2
Storage (MB)
714.2
Engine
Antfly
Passages
2,000,000
p95 (ms)
19.81
nDCG@10
0.433
Recall@100
0.813
Peak memory (MB)
2,755.6
Storage (MB)
1,649.0
Engine
Elasticsearch
Passages
2,000,000
p95 (ms)
6.49
nDCG@10
0.453
Recall@100
0.866
Peak memory (MB)
1,917.4
Storage (MB)
947.0
Engine
Quickwit
Passages
2,000,000
p95 (ms)
25.70
nDCG@10
0.459
Recall@100
0.880
Peak memory (MB)
1,323.3
Storage (MB)
1,422.2
Engine
Antfly
Passages
3,000,000
p95 (ms)
27.12
nDCG@10
0.385
Recall@100
0.751
Peak memory (MB)
3,530.8
Storage (MB)
2,201.6
Engine
Elasticsearch
Passages
3,000,000
p95 (ms)
9.43
nDCG@10
0.425
Recall@100
0.849
Peak memory (MB)
1,973.7
Storage (MB)
1,416.2
Engine
Quickwit
Passages
3,000,000
p95 (ms)
25.93
nDCG@10
0.429
Recall@100
0.858
Peak memory (MB)
1,569.8
Storage (MB)
2,003.0

Methodology

  • Antfly, Elasticsearch 9.5.2 and Quickwit 0.9.0 in one run on a Google Cloud c4a-standard-16 VM (Google Axion ARM64, 16 vCPUs, 62.7 GiB), measured Nov 13, 2026.
  • Every system indexes the same passages, and each smaller corpus is contained in the larger ones. Each run sends ten warm-up queries, then all 799 queries one at a time in three passes; the last pass is reported.
  • Antfly runs as a single shard. After indexing, Elasticsearch is force-merged into one segment; Antfly gets no equivalent explicit compaction step, though it may still compact on its own. All three engines store the passage text.
04

Vector search

VectorDBBench on 1M 768-dimensional vectors, with every system tuned to about 95% recall: query latency, throughput, memory and index build time. 50K and filtered-search results are in Details.

Serial query p95

One client. Lower is better.

One client. Lower is better.. Antfly: Antfly, 9.633 ms. Chroma: Chroma, 6.133 ms. Elasticsearch: Elasticsearch, 3.133 ms. Postgres + pgvector: Postgres + pgvector, 10.200 ms. Weaviate: Weaviate, 5.200 ms. Milvus: Milvus, 1.900 ms

  • Antfly 0.3
  • Other systems

Peak throughput

Best rate across concurrency levels. Higher is better.

Best rate across concurrency levels. Higher is better.. Antfly: Antfly, 920/s. Chroma: Chroma, 242/s. Elasticsearch: Elasticsearch, 3,091/s. Postgres + pgvector: Postgres + pgvector, 1,144/s. Weaviate: Weaviate, 1,348/s. Milvus: Milvus, 3,379/s

  • Antfly 0.3
  • Other systems

Peak memory

Lower is better.

Lower is better.. Antfly: Antfly, 4,627 · 10,448 MB. Chroma: Chroma, 3,698 · 7,334 MB. Elasticsearch: Elasticsearch, 2,058 · 11,136 MB. Postgres + pgvector: Postgres + pgvector, 2,320 · 12,004 MB. Weaviate: Weaviate, 7,336 · 12,264 MB. Milvus: Milvus, 12,179 · 15,492 MB

  • Memory it can’t release
  • Including page cache
  • Antfly 0.3
  • Other systems

Index build time

Insert 1M vectors until the index reports all of them. Lower is better.

Insert 1M vectors until the index reports all of them. Lower is better.. Antfly: Antfly, 284 s. Chroma: Chroma, 837 s. Elasticsearch: Elasticsearch, 480 s. Postgres + pgvector: Postgres + pgvector, 812 s. Weaviate: Weaviate, 678 s. Milvus: Milvus, 586 s

  • Antfly 0.3
  • Other systems
Details

Antfly results are means of three fresh indexes.

Tested versions

Chroma
1.5.9
Elasticsearch
9.5.2
Postgres + pgvector
0.8.6 (PostgreSQL 16)
Weaviate
1.39.2
Milvus
2.6.22
Antfly
v0.3.0

1M vectors, 768 dimensions

Engine
Antfly
Recall
0.9627
Peak QPS
920.1
p95 (ms)
9.633
Memory excl. page cache (MB)
4,627.0
Storage (MB)
5,969.5
Index build (s)
284
Engine
Chroma 1.5.9
Recall
0.9562
Peak QPS
241.6
p95 (ms)
6.133
Memory excl. page cache (MB)
3,697.7
Storage (MB)
3,459.7
Index build (s)
837
Engine
Elasticsearch 9.5.2
Recall
0.9602
Peak QPS
3,090.9
p95 (ms)
3.133
Memory excl. page cache (MB)
2,057.5
Storage (MB)
3,148.2 (provisional)
Index build (s)
480
Engine
Milvus 2.6.22
Recall
0.9568
Peak QPS
3,379.2
p95 (ms)
1.900
Memory excl. page cache (MB)
12,178.9
Storage (MB)
25,413.7
Index build (s)
586
Engine
pgvector 0.8.6-pg16
Recall
0.9656
Peak QPS
1,144.0
p95 (ms)
10.200
Memory excl. page cache (MB)
2,320.3
Storage (MB)
9,329.0
Index build (s)
812
Engine
Weaviate 1.39.2
Recall
0.9563
Peak QPS
1,348.5
p95 (ms)
5.200
Memory excl. page cache (MB)
7,336.5
Storage (MB)
3,947.5
Index build (s)
678

50K vectors, 1,536 dimensions

Engine
Antfly
Recall
0.9621
Peak QPS
1,071.9
p95 (ms)
5.633
Memory excl. page cache (MB)
1,576.4
Storage (MB)
373.1
Engine
Chroma 1.5.9
Recall
0.9869
Peak QPS
182.0
p95 (ms)
7.567
Memory excl. page cache (MB)
461.0
Storage (MB)
332.7
Engine
Elasticsearch 9.5.2
Recall
0.9526
Peak QPS
4,605.3
p95 (ms)
1.800
Memory excl. page cache (MB)
1,938.3
Storage (MB)
312.1 (provisional)
Engine
Milvus 2.6.22
Recall
0.9629
Peak QPS
5,443.9
p95 (ms)
1.400
Memory excl. page cache (MB)
2,785.4
Storage (MB)
2,393.4
Engine
pgvector 0.8.6-pg16
Recall
0.9690
Peak QPS
2,889.1
p95 (ms)
4.067
Memory excl. page cache (MB)
2,303.7
Storage (MB)
1,524.0
Engine
Weaviate 1.39.2
Recall
0.9547
Peak QPS
1,037.4
p95 (ms)
5.833
Memory excl. page cache (MB)
976.5
Storage (MB)
391.4

Filtered search, 1% tenant filter

Engine
Antfly
Recall@100
1.0000
Peak QPS
616.7
Peak p99 (ms)
79.97
Memory excl. page cache (MB)
1,029.4
Storage (MB)
373.6
Engine
Elasticsearch 9.5.2
Recall@100
1.0000
Peak QPS
5,965.9
Peak p99 (ms)
11.78
Memory excl. page cache (MB)
1,916.0
Storage (MB)
312.3 (provisional)
Engine
Weaviate 1.39.2
Recall@100
1.0000
Peak QPS
1,170.9
Peak p99 (ms)
10.97
Memory excl. page cache (MB)
980.1
Storage (MB)
392.8
Engine
pgvector 0.8.6-pg16
Recall@100
0.9573
Peak QPS
163.8
Peak p99 (ms)
218.15
Memory excl. page cache (MB)
2,303.8
Storage (MB)
1,524.0
Engine
Chroma 1.5.9
Recall@100
0.9999
Peak QPS
112.0
Peak p99 (ms)
411.46
Memory excl. page cache (MB)
495.9
Storage (MB)
336.7

Methodology

  • Apple M4 Max, Docker Desktop Linux arm64 VM (10 CPUs, 19.5 GiB), measured Nov 13, 2026.
  • Search settings target at least 95% recall. Antfly’s 50K search effort was raised from 0.425 to 0.45 after a 0.949 result, so those queries were seen during tuning. Filtered search restricts each query to a tenant holding 1% of the data.