Unsloth models: prices and the hardware each needs
35 models, 0 sold per token by 0 vendors. Vendors are in alphabetical order; the price is the cheapest list price among them, per million tokens.
| Model | Size | Sold per token by | From, input | Output | GPU memory |
|---|---|---|---|---|---|
| DeepSeek-R1-BF16 | 684.49 B | not sold per token | 1711.2 GB | ||
| DeepSeek-V3 | 684.53 B | not sold per token | 855.7 GB | ||
| gemma-2-27b | 27.23 B | not sold per token | 68.1 GB | ||
| gemma-2-2b-it (unsloth) | 2.61 B | not sold per token | 6.5 GB | ||
| gemma-2b-it (unsloth) | 2.51 B | not sold per token | 6.3 GB | ||
| gemma-3-1b-it (unsloth) | 1 B | not sold per token | 2.5 GB | ||
| GLM-4.7-Flash (unsloth) | 31.22 B | not sold per token | 78 GB | ||
| gpt-oss-20b | 20.91 B | not sold per token | 13.1 GB | ||
| gpt-oss-20b-BF16 | 20.91 B | not sold per token | 52.3 GB | ||
| llama-2-7b | 6.74 B | not sold per token | 16.9 GB | ||
| llama-2-7b-chat | 6.74 B | not sold per token | 16.9 GB | ||
| llama-3-8b-Instruct | 8.03 B | not sold per token | 20.1 GB | ||
| Llama-3.1-8B (unsloth) | 8.03 B | not sold per token | 20.1 GB | ||
| Llama-3.1-8B-Instruct (unsloth) | 8.03 B | not sold per token | 20.1 GB | ||
| Llama-3.2-1B (unsloth) | 1.24 B | not sold per token | 3.1 GB | ||
| Llama-3.2-1B-Instruct (unsloth) | 1.24 B | not sold per token | 3.1 GB | ||
| Llama-3.2-3B (unsloth) | 3.21 B | not sold per token | 8 GB | ||
| Llama-3.2-3B-Instruct (unsloth) | 3.21 B | not sold per token | 8 GB | ||
| Llama-3.3-70B-Instruct | 70.55 B | not sold per token | 176.4 GB | ||
| Meta-Llama-3.1-70B | 70.55 B | not sold per token | 176.4 GB | ||
| Meta-Llama-3.1-8B (unsloth) | 8.03 B | not sold per token | 20.1 GB | ||
| Meta-Llama-3.1-8B-Instruct (unsloth) | 8.03 B | not sold per token | 20.1 GB | ||
| Mistral-Small-24B-Instruct-2501 | 23.57 B | not sold per token | 58.9 GB | ||
| orpheus-3b-0.1-ft (unsloth) | 3.3 B | not sold per token | 8.2 GB | ||
| Qwen2.5-1.5B-Instruct (unsloth) | 1.54 B | not sold per token | 3.9 GB | ||
| Qwen2.5-14B-Instruct (unsloth) | 14.77 B | not sold per token | 36.9 GB | ||
| Qwen2.5-3B-Instruct (unsloth) | 3.09 B | not sold per token | 7.7 GB | ||
| Qwen2.5-7B-Instruct (unsloth) | 7.62 B | not sold per token | 19.1 GB | ||
| Qwen2.5-Coder-32B | 32.76 B | not sold per token | 81.9 GB | ||
| Qwen2.5-Coder-7B-Instruct (unsloth) | 7.62 B | not sold per token | 19.1 GB | ||
| Qwen3-4B-Base (unsloth) | 4.02 B | not sold per token | 10 GB | ||
| Qwen3-4B-Instruct-2507 (unsloth) | 4.02 B | not sold per token | 10 GB | ||
| Qwen3-8B (unsloth) | 8.19 B | not sold per token | 20.5 GB | ||
| Qwen3-Coder-Next-FP8 (unsloth) | 79.67 B | not sold per token | 99.6 GB | ||
| Qwen3-Embedding-4B (unsloth) | 4.02 B | not sold per token | 10 GB |