Open Source
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.
22
Models
—
Top Rank
—
Avg Capability
90.4K
Downloads
137
Likes
22
Open Models
Pricing Posture
0 / 22 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
Specialized
DeepSeek-V4-Flash leads current estimated value at ---.
Deployment Reach
15 / 22 models have verified deploy or runtime access
12 on your computer · 0 cloud servers you control · 5 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 · 0 desktop GPU fits · 0 cloud GPU fits · 0 high-memory cloud fits
Open Source
11
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.
Qwen3.6-35B-A3B-GGUF is now available through local Ollama runtime. 256K context window listed. Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
| # | Model | Category | Params | Capability | Downloads | Cheapest Verified | Est. Value | Open |
|---|---|---|---|---|---|---|---|---|
| — | DeepSeek-V4-Flash | LLMs | Unknown |
Qwen3.6-35B-A3B-GGUF is now available through local Ollama runtime. 256K context window listed. Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
Qwen3.6-27B-NVFP4 is now available through local Ollama runtime. 256K context window listed. Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
View sourceQwen3.6-35B-A3B-MTP-GGUF is now available through local Ollama runtime. 256K context window listed. Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
View sourceQwen3.6-35B-A3B-UD-MLX-4bit is now available through local Ollama runtime. 256K context window listed. Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
View sourceQwen3.6-27B-GGUF is now available through local Ollama runtime. 256K context window listed. Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
View sourceQwen3.6-27B-MTP-GGUF is now available through local Ollama runtime. 256K context window listed. Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
View sourceQwen3.6-27B-NVFP4 is now available through local Ollama runtime. 256K context window listed. Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
View sourceQwen3.6-35B-A3B-MTP-GGUF is now available through local Ollama runtime. 256K context window listed. Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
View sourceQwen3.6-35B-A3B-UD-MLX-4bit is now available through local Ollama runtime. 256K context window listed. Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
View source| — |
| 2.0K |
Custom Deploy |
| --- |
| — | DeepSeek-V4-Pro | LLMs | Unknown | — | 859 | Custom Deploy | --- |
| — | GLM-5.1-GGUF | LLMs | Unknown | — | 0 | Free Free | --- |
| — | MiniMax-M2.5-GGUF | LLMs | Unknown | — | 0 | $0.3000/M Cheapest verified | --- |
| — | MiniMax-M2.7-GGUF | LLMs | Unknown | — | 0 | Free Free | --- |
| — | GLM-4.7-Flash-GGUF | LLMs | Unknown | — | 0 | Custom Start Free Trial | --- |
| — | NVIDIA-Nemotron-3-Super-120B-A12B-GGUF | LLMs | 120B | — | 0 | Custom Start Free Trial | --- |
| — | NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF | LLMs | 30B | — | 0 | Custom Start Free Trial | --- |
| — | Qwen3.6-35B-A3B-UD-MLX-4bit | Specialized | 35B | — | 87.6K | Custom Start Free Trial | --- |
| — | LTX-2.3-GGUF | Specialized | Unknown | — | 0 | Free Free | --- |
| — | Kimi-K2.6-GGUF | Specialized | Unknown | — | 0 | Free Free | --- |
| — | Qwen3.5-2B-GGUF | Specialized | 2B | — | 0 | Custom Start Free Trial | --- |
| — | ERNIE-Image-GGUF | Image Gen | Unknown | — | 0 | Free Free | --- |
| — | Qwen3.6-27B-GGUF | Specialized | 27B | — | 0 | Custom Start Free Trial | --- |
| — | Qwen3.5-0.8B-GGUF | Specialized | 800M | — | 0 | Custom Start Free Trial | --- |
| — | granite-4.1-8b-GGUF | Specialized | 8B | — | 0 | Custom Start Free Trial | --- |
| — | Qwen3.5-4B-MTP-GGUF | Specialized | 4B | — | 0 | Custom Start Free Trial | --- |
| — | ERNIE-Image-Turbo-GGUF | Image Gen | Unknown | — | 0 | Free Free | --- |
| — | Qwen3.6-35B-A3B-MTP-GGUF | Specialized | 35B | — | 0 | Custom Start Free Trial | --- |
| — | Mistral-Medium-3.5-128B-GGUF | Specialized | 128B | — | 0 | Custom Start Free Trial | --- |
| — | Mistral-Small-4-119B-2603-GGUF | Specialized | 119B | — | 0 | Custom Start Free Trial | --- |
| — | gemma-4-E2B-it-GGUF | Specialized | 2B | — | 0 | Custom Start Free Trial | --- |