Plain-language provider view: what this company is strongest at, how many active models it has, what pricing we can verify, and which current models matter most.
39
Models
—
Top Rank
—
Avg Capability
949.0K
Downloads
937
Likes
39
Open Models
Pricing Posture
0 / 39 models have official company pricing
This tells you how often we can verify direct first-party pricing instead of only broker or router pricing.
Lowest Verified Entry
Free/M
The lowest reliable public price we could verify across this provider's active lineup.
Strategic Strength
LLMs
Llama-3.1-8B-Instruct leads current estimated value at ---.
Deployment Reach
21 / 39 models have verified deploy or runtime access
17 on your computer · 0 cloud servers you control · 4 hosted for you
Open weights do not always mean easy hosted access. For unsloth, they usually mean you bring the hardware yourself or rent a cloud GPU when the models are larger.
Most open models here can run on your own hardware.
22 easy personal-hardware fits · 12 desktop GPU fits · 3 cloud GPU fits · 2 high-memory cloud fits
Open Source
2
Recent launches, pricing moves, benchmark updates, API changes, and research signals linked to this provider.
Recent updates about new ways to use this provider's models, including self-host and official runtime options.
tinyllama is now available through local Ollama runtime. 2K context window listed. The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.
| # | Model | Category | Params | Capability | Downloads | Cheapest Verified | Est. Value | Open |
|---|---|---|---|---|---|---|---|---|
| — | Llama-3.1-8B-Instruct | LLMs | 8B |
tinyllama is now available through local Ollama runtime. 2K context window listed. The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.
SmolLM2-1.7B-Instruct-GGUF is now available through local Ollama runtime. 8K context window listed. SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.
View sourceSmolLM2-1.7B-Instruct-GGUF is now available through local Ollama runtime. 8K context window listed. SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.
View source| — |
| 150.5K |
Price not verified View Plan |
| --- |
| — | Qwen2.5-Coder-7B-Instruct | LLMs | 8B | — | 125.6K | Price not verified View Plan | --- |
| — | Qwen2.5-0.5B-Instruct | LLMs | 494M | — | 27.7K | Price not verified View Plan | --- |
| — | Qwen3-4B-Instruct-2507 | LLMs | 4B | — | 27.0K | Price not verified View Plan | --- |
| — | Qwen2.5-1.5B-Instruct | LLMs | 2B | — | 20.3K | Price not verified View Plan | --- |
| — | gemma-3-270m-it | LLMs | 268M | — | 63.7K | Free Free | --- |
| — | Qwen3-VL-2B-Instruct | Multimodal | 2B | — | 11.8K | Price not verified View Plan | --- |
| — | Qwen3-4B-Base | LLMs | 4B | — | 11.0K | Price not verified View Plan | --- |
| — | Mistral-Small-3.2-24B-Instruct-2506 | Multimodal | 24B | — | 6.9K | Price not verified View Plan | --- |
| — | DeepSeek-OCR-2 | Multimodal | 3B | — | 4.7K | Free Free | --- |
| — | LFM2.5-230M | LLMs | 230M | — | 3.7K | Price not verified View Plan | --- |
| — | Qwen3-1.7B-Base | LLMs | 2B | — | 3.1K | Price not verified View Plan | --- |
| — | DeepSeek-R1-Distill-Qwen-7B | LLMs | 8B | — | 2.4K | Free Free | --- |
| — | tinyllama | LLMs | 1B | — | 1.2K | Price not verified View Plan | --- |
| — | GLM-4.7-Flash | LLMs | 31B | — | 1.2K | Price not verified View Plan | --- |
| — | GLM-5.3 | LLMs | 753B | — | 897 | Price not verified Deploy | --- |
| — | Kimi-K3 | Multimodal | Unknown | — | 803 | Price not verified Deploy | --- |
| — | Qwen3-30B-A3B-Thinking-2507 | LLMs | 31B | — | 539 | Price not verified View Plan | --- |
| — | Llama-3.2-90B-Vision-Instruct | Multimodal | 89B | — | 468 | Price not verified View Plan | --- |
| — | DeepSeek-V4-Flash | LLMs | Unknown | — | 428 | Price not verified Deploy | --- |
| — | Phi-4-mini-reasoning | LLMs | 4B | — | 349 | Price not verified View Plan | --- |
| — | DeepSeek-V4-Pro | LLMs | Unknown | — | 216 | Price not verified Deploy | --- |
| — | aya-vision-8b | Multimodal | 9B | — | 101 | Free Free | --- |
| — | Qwen-Image-2.1 | Image Gen | 7B | — | 345.9K | Free Free | --- |
| — | embeddinggemma-300m | Embeddings | 303M | — | 45.1K | Free Free | --- |
| — | orpheus-3b-0.1-ft | Speech | 3B | — | 43.5K | Free Free | --- |
| — | csm-1b | Speech | 2B | — | 7.5K | Free Free | --- |
| — | Qwen3-Embedding-0.6B | Embeddings | 596M | — | 7.2K | Price not verified View Plan | --- |
| — | sam3.1 | Specialized | Unknown | — | 6.8K | Free Free | --- |
| — | FLUX.2-VAE | Specialized | Unknown | — | 6.5K | Free Free | --- |
| — | embeddinggemma-2 | Embeddings | 744M | — | 6.3K | Free Free | --- |
| — | flux-3-image-klein | Image Gen | 6B | — | 4.2K | Free Free | --- |
| — | Llama-OuteTTS-1.0-1B | Speech | 1B | — | 4.1K | Free Free | --- |
| — | GLM-OCR | Vision | 1B | — | 3.4K | Price not verified View Plan | --- |
| — | flux-3-image-klein-base | Image Gen | 6B | — | 1.9K | Free Free | --- |
| — | Spark-TTS-0.5B | Speech | 500M | — | 838 | Free Free | --- |
| — | CrisperWhisper | Speech | 2B | — | 789 | Free Free | --- |
| — | embeddinggemma-300m-qat-q8_0-unquantized | Embeddings | 303M | — | 276 | Free Free | --- |
| — | embeddinggemma-300m-qat-q4_0-unquantized | Embeddings | 303M | — | 166 | Free Free | --- |