App	Type	Opens it as	Systems	Engine	Start
LM Studio	Desktop app	MLX	macOSWindowsLinux	llama.cpp, MLX	Open in LM Studio
Jan	Desktop app	MLX	macOSWindowsLinux	llama.cpp, MLX	Get Jan
MLX LM	CLI + API	MLX	macOS	MLX	`mlx_lm.chat --model mlx-community/Leanstral-2603-8bit`
vLLM	Server	Original weights	WSLWindowsLinux	vLLM	`vllm serve mistralai/Leanstral-2603`
SGLang	Server	Original weights	WSLWindowsLinux	SGLang	`python3 -m sglang.launch_server --model-path mistralai/Leanstral-2603`
Docker Model Runner	CLI + API	Original weights	macOSWindowsLinux	llama.cpp, vLLM	`docker model run hf.co/mistralai/Leanstral-2603`
Unsloth Desktop	Desktop app	MLX	macOSWindowsLinux	llama.cpp, MLX, stable-diffusion.cpp	Get Unsloth Desktop
Atomic Chat	Desktop app	MLX	macOSWindowsLinux	llama.cpp, MLX-VLM	Open in Atomic Chat
Text Generation WebUI	Desktop app	Original weights	macOSWindowsLinux	llama.cpp, Transformers, ExLlamaV3	Get Text Generation WebUI
Msty Studio	Desktop app	MLX	macOSWindowsLinux	Ollama, llama.cpp, MLX	Get Msty Studio
Inferencer	Desktop app	MLX	macOS	MLX	Get Inferencer
exo	Server	MLX	macOSLinux	MLX	Get exo

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps. Try another context length.

KV cache: latent (MLA) KV cache.

Quantization	Quality	Weights	Total at 8K context	Total at 32K context	Download
`Q2_K`	Low	47.8 GB	48.5 GB	49.1 GB	All files (opens in a new tab)
`Q3_K_M`	Low	58.5 GB	59.3 GB	59.9 GB	All files (opens in a new tab)
`Q4_K_M`	Good	72.8 GB	73.6 GB	74.2 GB	All files (opens in a new tab)
`Q5_K_M`	High	84.8 GB	85.6 GB	86.1 GB	All files (opens in a new tab)
`Q6_K`	High	97.9 GB	98.7 GB	99.3 GB	All files (opens in a new tab)
`Q8_0`	Very high	127 GB	127 GB	128 GB	All files (opens in a new tab)
`F16`	Full	239 GB	240 GB	240 GB	Original weights (opens in a new tab)

Best hardware for Leanstral 119B-A6B

The least expensive GPU in our catalog that runs it without offloading is the NVIDIA RTX PRO 6000 Blackwell (launch price $8,565) at Q4_K_M.

Quality	Hardware	Quant	Memory	Speed	Runs
74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (256 GB)	`Q8_0`	143 GB / 192 GB	53.9 tok/s	Runs great
73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	Apple M2 Ultra (192 GB)	`Q6_K`	110 GB / 144 GB	68.1 tok/s	Runs great
71Great quality (A) · 71 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GB10 (128 GB)	`Q5_K_M`	94.8 GB / 115 GB	37.1 tok/s	Runs great
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	Apple M4 Max (128 GB)	`Q4_K_M`	81.3 GB / 96.0 GB	68.4 tok/s	Runs great
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA RTX PRO 6000 Blackwell	`Q4_K_M`	78.4 GB / 96.0 GB	158 tok/s	Runs great
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA RTX Spark N1X (6144-core GPU) (128 GB)	`Q4_K_M`	81.8 GB / 102 GB	47.6 tok/s	Runs great
70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	AMD Ryzen AI Max+ 395 (128 GB)	`Q4_K_M`	81.3 GB / 96.0 GB	36.5 tok/s	Runs great
74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	Apple M3 Ultra (512 GB)	`Q8_0`	158 GB / 384 GB	53.9 tok/s	Runs great
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	Apple M1 Max (64 GB)	`Q2_K`	52.4 GB / 48.0 GB	68.1 tok/s	Runs wellover GPU memory limit
51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	Apple M4 Max (64 GB)	`Q2_K`	52.4 GB / 48.0 GB	85.1 tok/s	Runs wellover GPU memory limit

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.