Catalog

Models

Every model the book trades. Filter by size, quantization, context window, or price, and open one to see its live order book.

29 models

Model		Quant			Hosted
Mistral Medium 3.5 128B78 GB weights	128B	Q4_K_M	131K	—	$0.700	—	—
GPT-OSS 120B63 GB weights	120B	Q4_K_M	131K	—	$0.600	—	—
Llama 3.3 70B Instruct43 GB weights	70B	Q4_K_M	131K	—	$0.600	—	—
Laguna XS 2.1 33B A3B20 GB weights	33B-A3B	Q4_K_M	262K	—	$0.500	—	—
Qwen2.5 Coder 32B20 GB weights	32B	Q4_K_M	33K	—	$0.500	—	—
Qwen3 32B20 GB weights	32B	Q4_K_M	33K	—	$0.500	—	—
Qwen3.8 32B20 GB weights	32B	Q4_K_M	33K	—	$0.500	—	—
Qwen3 30B A3B18.6 GB weights	30B-A3B	Q4_K_M	33K	—	$0.300	—	—
Qwen3 Coder 30B18.6 GB weights	30B-A3B	Q4_K_M	262K	—	$0.500	—	—
Muse Glimmer 30B18.3 GB weights	30B	Q4_K_M	131K	—	$0.490	—	—
Nemotron 3.5 Lightning 30B A3B18.3 GB weights	30B-A3B	Q4_K_M	131K	—	$0.300	—	—
Gemma 2 27B IT16.5 GB weights	27B	Q4_K_M	8K	—	$0.400	—	—
Qwen3.5 27B16.5 GB weights	27B	Q4_K_M	33K	—	$0.450	—	—
Qwen3.8 27B16.5 GB weights	27B	Q4_K_M	33K	—	$0.450	—	—
Gemma 4 26B15.9 GB weights	26B	Q4_K_M	131K	—	$0.420	—	—
Mistral Small 24B14.5 GB weights	24B	Q4_K_M	33K	—	$0.400	—	—
GPT-OSS 20B13 GB weights	20B	Q4_K_M	131K	—	$0.260	—	—
DeepSeek R1 Distill 14B9 GB weights	14B	Q4_K_M	131K	—	$0.300	—	—
Qwen3 14B9 GB weights	14B	Q4_K_M	33K	—	$0.300	—	—
Qwen3.8 14B9 GB weights	14B	Q4_K_M	33K	—	$0.300	—	—
Gemma 4 12B7.3 GB weights	12B	Q4_K_M	131K	—	$0.280	—	—
Llama 3.1 8B Instruct4.9 GB weights	8B	Q4_K_M	131K	—	$0.240	—	—
Qwen3 8B5 GB weights	8B	Q4_K_M	33K	—	$0.240	—	—
LFM2.5 8B A1B4.9 GB weights	8B-A1B	Q4_K_M	33K	—	$0.240	—	—
Granite 4.1 8B4.9 GB weights	8B	Q4_K_M	131K	—	$0.240	—	—
Qwen3.8 8B5 GB weights	8B	Q4_K_M	33K	—	$0.240	—	—
LLaMA-Mesh 8B4.9 GB weights	8B	Q4_K_M	131K	—	$0.240	—	—
Qwen3.5 4B2.4 GB weights	4B	Q4_K_M	33K	—	$0.165	—	—
Qwen3.8 4B2.4 GB weights	4B	Q4_K_M	33K	—	$0.165	—	—