← Download & Install · Getting Started · Deployment Guide · raw markdown

Measured Performance

All numbers below are measured on real deployments of the shipping build — not projections. CPU results are from production-class cloud nodes (32 vCPU / 64 GB); GPU results from a single NVIDIA L4. Decode tokens/sec is the per-user response speed; 20+ tokens/sec is faster than reading speed.

per-user tokens/secfast prompt processing ~0.1 s cached follow-ups multimodal response times GPU ≈ 10× CPUcluster scaling

Architectures tested

ArchitectureNode class testedNotes
Arm — AWS Graviton4c9g · 32 cores / 64 GB · 3.3 GHz Fastest CPU decode per node (highest memory bandwidth); one binary serves all Arm hosts
Intel Xeonc8i · 32 vCPU / 64 GB · 3.9 GHz Same x86_64 binary as AMD; strong prompt processing
AMD EPYC (Turin)c8a · 32 cores / 64 GB · 2.6 GHz Same x86_64 binary as Intel; current AMD generation
NVIDIA GPUL4 (24 GB) measured · add-on also runs A100, A10/A10G, RTX 40-series, H100 One-flag install add-on; ~10× CPU speeds at ~96% of the hardware's practical ceiling

Two binaries cover every deployment: one for Arm, one for x86_64 (Intel and AMD). Clusters can mix architectures freely — see cluster scaling below.

Text generation — per-user speed (tokens/sec)

ModelCPU · Arm (Graviton)CPU · IntelCPU · AMDGPU · NVIDIA L4
2B chat + vision514241138
4B chat + vision (recommended)24202970
35B mixture-of-experts13–19

Single-stream warm decode (256-token answer, greedy), quantized models, 8-bit KV cache; table figures from 32-vCPU nodes. Decode follows memory bandwidth, so node size matters: 4B measures ≈24 tok/s on a 32-vCPU Graviton (c9g.8xlarge) and ≈23 tok/s on a 16-vCPU (c9g.4xlarge). A GPU node serves the same API roughly 10× faster.

Prompt processing & multi-user throughput (2B, per node)

NodePrompt processing (tok/s)8 concurrent users — aggregate (tok/s)
Arm (Graviton c9g)30788
Intel (c8i)13128
AMD (c8a, current gen)22144

Prompt processing measured on a 3,000-token document with a cold cache; a repeat question on the same document answers from the built-in prompt cache in ~0.1 s. Concurrency figures are aggregate output tokens/sec across 8 simultaneous clients issuing short chat requests (64-token answers) — a worst-case bursty pattern; sustained generation aggregates higher. Prompt processing sets time-to-first-token on long documents and scales with vCPU count. Under concurrency the batcher raises aggregate throughput while each user's share falls; max-inflight controls admission (validated stable to 64 concurrent on a 64 GB node).

Multimodal — full request response times

Capability (CPU node)2B4B
Image question (photo, chart, form)~8 s~13 s
Video question (multi-frame)~17 s~28 s
Speech-to-text (short clip)2–4 s (dedicated model)
Text-to-speech (sentence)~8 s (dedicated model)
Long-document outline (1,000+ words)~10 s~23 s

Averages across a 380-prompt validation suite on a CPU node — complete round trip including prompt processing and the full answer.

Capability (GPU · L4)Warm response
Image / video questiona few hundred ms + answer tokens
Speech-to-text (short clip)~200 ms
Prompt processingsub-second
Image editing (20-step, 20B editor)~81 s

Text-to-speech runs on CPU in this release (it is fast there). Image editing is GPU-recommended; CPU-only edits take minutes.

Cluster scaling — adding nodes for more users

Concurrent requests3-node cluster (4B) — aggregate tok/svs single nodePer-node memory
1643.81.49×16 GB
3243.21.52×23 GB
6447.71.65×31 GB

Tested cluster: three 32-vCPU / 64 GB nodes — one Arm (Graviton4, c9g.8xlarge), one Intel Xeon (c8i.8xlarge), one AMD EPYC (c7a.8xlarge) — with the Graviton as the entry node. Any node accepts requests and load-balances across the fleet; scaling efficiency improves as concurrency rises and each node stays independently memory-bounded — so capacity grows with node count. Mixed-architecture clusters are supported (the measured fleet above combined all three CPU vendors); requests route by capacity and model residency — a request for any model reaches a node that has it loaded, so a mixed fleet can serve different models behind one endpoint — with the fastest node as the entry point. See the Deployment Guide for the two-command cluster join.

Methodology

Text throughput measured with greedy decoding on quantized production models (8-bit KV cache, fast prompt processing and fast attention kernels enabled — the installer defaults) on 32 vCPU / 64 GB cloud nodes; GPU figures from a single NVIDIA L4 at ~96% of the hardware's practical ceiling. Multimodal times are averages over a 380-prompt validation suite covering 13 industries, measured client-side as complete request round trips. Every release is gated on that suite plus a concurrency sweep on all three CPU architectures before binaries are published. First request after installing a model additionally pays a one-time disk load (seconds to ~1 minute depending on model size and storage).