Mistral
Leanstral 119B A6B (119B parameters) requires approximately 84.4 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 6.5B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 98 GB of VRAM.
Get started
— copy & paste to run locallyCopy-paste commands to run Leanstral 119B A6B on your machine.
Run
docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
--hf-repo "mistralai/Leanstral-2603" \
--hf-file "Leanstral-2603-Q4_K_M.gguf" \
-c 4096 -ngl 99Quick specs
About this model
Related models
Quick picks
Best hardware
Run this model
Quantization options
No hardware detected — fit column shows raw VRAM estimates
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 46.4 GB | Low | — |
Q3_K_S | 3 | 58.3 GB | Low | — |
NVFP4 | 4 | 66.6 GB | Medium | — |
Q4_K_M | 4 | 72.6 GB | Medium | — |
Q5_K_M | 5 | 85.7 GB | High | — |
Q6_K | 6 | 97.6 GB | High | — |
Q8_0 | 8 | 127.3 GB | Very High | — |
F16 | 16 | 244.0 GB | Maximum | — |
Hardware compatibility
Computing compatibility...
Memory breakdown
Frequently asked questions
Leanstral 119B A6B (119B parameters) requires approximately 84.4 GB of VRAM with Q4_K_M quantization. Lower quantizations like Q4_K_M use less memory but may reduce quality.
Yes, Mac Studio M3 Ultra 256GB can run Leanstral 119B A6B with a compatibility score of 85/100. It provides 256 GB of memory and achieves approximately 17.0 tokens per second.
The recommended quantization for Leanstral 119B A6B is Q4_K_M, which offers the best balance between model quality and memory efficiency. Higher quantizations preserve more quality but require more VRAM.
The top recommended hardware for Leanstral 119B A6B: AMD Instinct MI300A 128GB (score: 93/100), NVIDIA H200 141GB (score: 93/100), NVIDIA H200 PCIe 141GB (score: 93/100). These provide the best combination of memory, bandwidth, and compute for running this model locally.
Yes, Leanstral 119B A6B is well-suited for coding as well as reasoning, agentic, vision, research. It was designed with these use cases in mind.
See also
