Apertus v1.5 8B
Deployable
Swiss, multilingual and compact, with text, image and audio input. A candidate for controlled RAG after exact task evaluation.
Model intelligence
Choose the model after the workload.
A model is deployable only when its weights, licence, serving engine, memory envelope and behaviour all fit. This catalogue separates those facts — and dates every conclusion.
Official model factsCalculated memory plansRegistry verified 29 July 2026 · Kimi K3 review by 12 August 2026
Compare the wider open-model candidate programme, use cases and benchmark gates →
Explore the deployment catalogue
Filter by the system you want to own, not by a leaderboard headline.
12 models shown
Apertus v1.5 70B
Deployable
A Swiss large-model candidate with text, image and audio input; exact multimodal and long-context workloads require measurement.
gpt-oss-20b
Deployable
A compact reasoning and tool-use candidate. Active parameters affect compute, not the full weight-residency requirement.
gpt-oss-120b
Deployable
The official single-80-GB fit is a weight/runtime claim, not a multi-user throughput promise. Concurrency is benchmarked separately.
Qwen3.5 27B
Deployable
A compact multimodal option for document and vision workflows, subject to exact quantisation and context evaluation.
Kimi Linear 48B-A3B
Deployable
Interesting for long-context private archives. Published cache and latency advantages remain vendor/research evidence until measured on the delivery stack.
Kimi K2
Large-system
Rack-class despite 32B active parameters: the expert weights must remain resident. The official deployment guide is the sizing anchor.
Kimi K2.5
Large-system
Multimodal and more memory-efficient than FP8, but still a multi-GPU system whose context and concurrency must be proven.
Kimi K2.6
Large-system
A current multimodal checkpoint with image input. Local video is not claimed: the official card describes video support as experimental and API-only.
Kimi K2.7 Code
Coding specialist
A coding-agent derivative with preserved reasoning traces and image input. It is evaluated as a specialist, not assumed to be the default archive model.
DeepSeek V3
Large-system
A large MoE candidate where the custom model licence and validated multi-GPU serving path fit the client's governance boundary.
Kimi K3
Rack programmeUnmeasured by ANULUM
Official weights now unblock a sovereign evaluation and rack-architecture programme. Production remains gated by exact engine, context, concurrency, tool-schema, security, quality and licence acceptance; current public serving guidance supports image input, not video or audio.
Kimi without the fog
The Kimi name spans very different deployment realities. Linear can fit a professional node when quantised. K2 through K2.7 are large-system programmes. K3 is now an open-weight, rack-scale candidate: available for controlled evaluation and architecture work, but not pre-validated production.
Parameter honesty: active parameters estimate compute per token. Total resident weights, KV cache, runtime buffers, context and concurrency determine memory.
A catalogue is not a claim that every model is open source.
This page uses open weight for downloadable checkpoints under publisher terms and reserves open source for exact versions whose artefacts and licences support that description. Licence, checkpoint provenance and intended use are reviewed before deployment.
Benchmark status: publisher scores remain publisher evidence. No card on this page carries an ANULUM quality score unless a reproducible ANULUM run is linked.
Primary evidence
- Official Moonshot AI model catalogue ↗
- Official Kimi K2 deployment guidance ↗
- Official Kimi K2.6 model card ↗
- Official Kimi K2.7 Code model card ↗
- Official Kimi K3 model card and weights ↗
- Kimi K3 License ↗
- Official vLLM Kimi K3 deployment recipe ↗
- SGLang Kimi K3 serving cookbook ↗
- Swiss AI Apertus v1.5 70B model card ↗
- Official gpt-oss release and deployment notes ↗
A source link does not constitute an ANULUM quality endorsement. Model selection follows evaluation on the client's tasks and constraints.