iilib

Open Models Research

Compare open-weight models without treating every checkpoint as a separate product.

This view is generated from iilib's shared model graph. It focuses on representative, source-backed models and separates downloadable weights, licensing, commercial-use terms, architecture, self-hostability and research transparency.

“Open-weight” does not automatically mean “open source.” Custom community and vendor licenses remain visible instead of being collapsed into a single open/closed label.

Open-model records
19
Model families
13
Self-hostable
19
Mapped to an API
2

Openness signals

Weights are only one part of the picture

4 models explicitly expose source code or recipes; 2 expose public training data; 2 expose training checkpoints. Missing transparency fields are not inferred from marketing language.

Method

Family, developer and hosted API availability are derived from verified graph relationships. Use-case labels are editorial research taxonomy, not benchmark rankings.

Read the research methodology →

Research table

Filter the current representative set

Filters run only in your browser and do not create indexable URL combinations. The default table remains the canonical research view.

19 models shown
Self-hostable
Family
DeepSeek R1
Context
128K
Parameters
671B
Architecture
Moe
Weights
Downloadable
License
MIT
ReasoningCoding
0 mapped APIsView model →
Self-hostable
Family
DeepSeek V3
Context
128K
Parameters
671B
Architecture
Moe
Weights
Downloadable
License
MIT
General ChatCoding
0 mapped APIsView model →
Self-hostable
Family
Gemma 4
Context
256K
Parameters
11.95B
Architecture
Dense
Weights
Downloadable
License
Apache-2.0
General ChatReasoningCoding
0 mapped APIsView model →
Self-hostable
Family
Gemma 4
Context
256K
Parameters
25.2B
Architecture
Moe
Weights
Downloadable
License
Apache-2.0
General ChatReasoningCoding
0 mapped APIsView model →
Self-hostable
Family
GLM-5.3
Context
1.05M
Parameters
744B
Architecture
Moe
Weights
Downloadable
License
GLM-5.3 License
CodingReasoning
0 mapped APIsView model →
Self-hostable
Family
GLM-5.3
Context
1.05M
Parameters
320B
Architecture
Hybrid
Weights
Downloadable
License
MIT
CodingReasoningVision Multimodal
0 mapped APIsView model →
Self-hostable
Family
gpt-oss
Context
131K
Parameters
116.83B
Architecture
Moe
Weights
Downloadable
License
Apache-2.0
ReasoningCoding
1 mapped APIView model →
Kimi K3
Moonshot AI
Self-hostable
Family
Kimi K3
Context
1.05M
Parameters
2,800B
Architecture
Moe
Weights
Downloadable
License
Kimi K3 License
CodingReasoningVision Multimodal
0 mapped APIsView model →
Self-hostable
Family
Llama 4
Context
1M
Parameters
400B
Architecture
Moe
Weights
Restricted
License
Llama 4 Community License
General ChatVision MultimodalMultilingual
0 mapped APIsView model →
Self-hostable
Family
Llama 4
Context
10M
Parameters
109B
Architecture
Moe
Weights
Restricted
License
Llama 4 Community License
General ChatVision MultimodalMultilingual
0 mapped APIsView model →
Self-hostable
Family
Mistral Medium
Context
256K
Parameters
128B
Architecture
Dense
Weights
Downloadable
License
Modified MIT
General ChatReasoningCoding
1 mapped APIView model →
Self-hostable
Family
Nemotron 3.5
Context
1M
Parameters
30B
Architecture
Hybrid
Weights
Downloadable
License
OpenMDW-1.1
ReasoningCodingGeneral Chat
0 mapped APIsView model →
Self-hostable
Family
Olmo 3
Context
66K
Parameters
7B
Architecture
Dense
Weights
Downloadable
License
Apache-2.0
General Chat
0 mapped APIsView model →
Self-hostable
Family
Olmo 3
Context
66K
Parameters
32B
Architecture
Dense
Weights
Downloadable
License
Apache-2.0
ReasoningCoding
0 mapped APIsView model →
Qwen3-235B-A22B
Alibaba Cloud
Self-hostable
Family
Qwen3
Context
128K
Parameters
235B
Architecture
Moe
Weights
Downloadable
License
Apache-2.0
General ChatReasoningCoding
0 mapped APIsView model →
Qwen3-30B-A3B
Alibaba Cloud
Self-hostable
Family
Qwen3
Context
128K
Parameters
30B
Architecture
Moe
Weights
Downloadable
License
Apache-2.0
General ChatReasoningCoding
0 mapped APIsView model →
Qwen3-4B
Alibaba Cloud
Self-hostable
Family
Qwen3
Context
32K
Parameters
4B
Architecture
Dense
Weights
Downloadable
License
Apache-2.0
General ChatReasoningCoding
0 mapped APIsView model →
Self-hostable
Family
Qwen3 Embedding
Context
32K
Parameters
0.6B
Architecture
Dense
Weights
Downloadable
License
Apache-2.0
Embedding
0 mapped APIsView model →
Qwen3-Reranker-0.6B
Alibaba Cloud
Self-hostable
Family
Qwen3 Reranker
Context
32K
Parameters
0.6B
Architecture
Dense
Weights
Downloadable
License
Apache-2.0
Reranking
0 mapped APIsView model →

What is intentionally missing?

The table does not mirror every parameter size, quantization, GGUF/AWQ/GPTQ conversion, community fine-tune, hosted alias or intermediate training checkpoint. A new Model record must add a meaningful research dimension.

No universal “best model” score

Benchmark leaderboards are excluded from this first research layer because evaluation versions, harnesses, prompts, contamination risk and provider settings differ. Structured facts remain separate from future benchmark evidence.