llama.cpp
llama.cpp, the name to use in providers=
- Models offered
- 46
- Billing currency
- USD
- Runs
- on your machine
- Fees
- none
Models
| Model | Model id here | Status | Input per 1M | Output per 1M |
|---|---|---|---|---|
| Gemma 3 12B IT | lmstudio-community/gemma-3-12b-it-GGUF:Q4_K_M | ga | $0 | $0 |
| Gemma 3 12B IT | lmstudio-community/gemma-3-12b-it-GGUF:Q6_K | ga | $0 | $0 |
| Gemma 3 12B IT | lmstudio-community/gemma-3-12b-it-GGUF:Q8_0 | ga | $0 | $0 |
| Gemma 3 27B IT | lmstudio-community/gemma-3-27b-it-GGUF:Q4_K_M | ga | $0 | $0 |
| Gemma 3 27B IT | lmstudio-community/gemma-3-27b-it-GGUF:Q6_K | ga | $0 | $0 |
| Gemma 3 27B IT | lmstudio-community/gemma-3-27b-it-GGUF:Q8_0 | ga | $0 | $0 |
| Gemma 3 4B IT | lmstudio-community/gemma-3-4b-it-GGUF:Q4_K_M | ga | $0 | $0 |
| Gemma 3 4B IT | lmstudio-community/gemma-3-4b-it-GGUF:Q6_K | ga | $0 | $0 |
| Gemma 3 4B IT | lmstudio-community/gemma-3-4b-it-GGUF:Q8_0 | ga | $0 | $0 |
| Gemma 4 31B IT | lmstudio-community/gemma-4-31B-it-GGUF:Q4_K_M | ga | $0 | $0 |
| Gemma 4 31B IT | lmstudio-community/gemma-4-31B-it-GGUF:Q6_K | ga | $0 | $0 |
| Gemma 4 31B IT | lmstudio-community/gemma-4-31B-it-GGUF:Q8_0 | ga | $0 | $0 |
| GPT OSS 120B | lmstudio-community/gpt-oss-120b-GGUF:MXFP4 | ga | $0 | $0 |
| GPT OSS 20B | lmstudio-community/gpt-oss-20b-GGUF:MXFP4 | ga | $0 | $0 |
| Llama-3.1-8B-Instruct | lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF:Q4_K_M | ga | $0 | $0 |
| Llama-3.1-8B-Instruct | lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF:Q5_K_M | ga | $0 | $0 |
| Llama-3.1-8B-Instruct | lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF:Q6_K | ga | $0 | $0 |
| Llama-3.1-8B-Instruct | lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF:Q8_0 | ga | $0 | $0 |
| Llama-3.3-70B-Instruct | lmstudio-community/Llama-3.3-70B-Instruct-GGUF:Q4_K_M | ga | $0 | $0 |
| Llama-3.3-70B-Instruct | lmstudio-community/Llama-3.3-70B-Instruct-GGUF:Q6_K | ga | $0 | $0 |
| Llama-3.3-70B-Instruct | lmstudio-community/Llama-3.3-70B-Instruct-GGUF:Q8_0 | ga | $0 | $0 |
| Qwen 2.5 7B Instruct Turbo | lmstudio-community/Qwen2.5-7B-Instruct-GGUF:Q4_K_M | ga | $0 | $0 |
| Qwen 2.5 7B Instruct Turbo | lmstudio-community/Qwen2.5-7B-Instruct-GGUF:Q6_K | ga | $0 | $0 |
| Qwen 2.5 7B Instruct Turbo | lmstudio-community/Qwen2.5-7B-Instruct-GGUF:Q8_0 | ga | $0 | $0 |
| Qwen2.5-Coder-32B-Instruct | lmstudio-community/Qwen2.5-Coder-32B-Instruct-GGUF:Q4_K_M | ga | $0 | $0 |
| Qwen2.5-Coder-32B-Instruct | lmstudio-community/Qwen2.5-Coder-32B-Instruct-GGUF:Q6_K | ga | $0 | $0 |
| Qwen2.5-Coder-32B-Instruct | lmstudio-community/Qwen2.5-Coder-32B-Instruct-GGUF:Q8_0 | ga | $0 | $0 |
| Qwen3 30B-A3B Instruct 2507 | lmstudio-community/Qwen3-30B-A3B-Instruct-2507-GGUF:Q4_K_M | ga | $0 | $0 |
| Qwen3 30B-A3B Instruct 2507 | lmstudio-community/Qwen3-30B-A3B-Instruct-2507-GGUF:Q6_K | ga | $0 | $0 |
| Qwen3 30B-A3B Instruct 2507 | lmstudio-community/Qwen3-30B-A3B-Instruct-2507-GGUF:Q8_0 | ga | $0 | $0 |
| Qwen3 32B | Qwen/Qwen3-32B-GGUF:Q4_K_M | ga | $0 | $0 |
| Qwen3 32B | Qwen/Qwen3-32B-GGUF:Q5_K_M | ga | $0 | $0 |
| Qwen3 32B | Qwen/Qwen3-32B-GGUF:Q6_K | ga | $0 | $0 |
| Qwen3 32B | Qwen/Qwen3-32B-GGUF:Q8_0 | ga | $0 | $0 |
| Qwen3 8B | Qwen/Qwen3-8B-GGUF:Q4_K_M | ga | $0 | $0 |
| Qwen3 8B | Qwen/Qwen3-8B-GGUF:Q5_K_M | ga | $0 | $0 |
| Qwen3 8B | Qwen/Qwen3-8B-GGUF:Q6_K | ga | $0 | $0 |
| Qwen3 8B | Qwen/Qwen3-8B-GGUF:Q8_0 | ga | $0 | $0 |
| Qwen3.5 9B | unsloth/Qwen3.5-9B-GGUF:Q4_K_M | ga | $0 | $0 |
| Qwen3.5 9B | unsloth/Qwen3.5-9B-GGUF:Q5_K_M | ga | $0 | $0 |
| Qwen3.5 9B | unsloth/Qwen3.5-9B-GGUF:Q6_K | ga | $0 | $0 |
| Qwen3.5 9B | unsloth/Qwen3.5-9B-GGUF:Q8_0 | ga | $0 | $0 |
| Qwen3.6 27B | unsloth/Qwen3.6-27B-GGUF:Q4_K_M | ga | $0 | $0 |
| Qwen3.6 27B | unsloth/Qwen3.6-27B-GGUF:Q5_K_M | ga | $0 | $0 |
| Qwen3.6 27B | unsloth/Qwen3.6-27B-GGUF:Q6_K | ga | $0 | $0 |
| Qwen3.6 27B | unsloth/Qwen3.6-27B-GGUF:Q8_0 | ga | $0 | $0 |
Built from catalog version 2026-11-04.3 of . Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).