Leanstral 119B-A6B on NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip

Can the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip run Leanstral 119B-A6B?

Yes, it runs great

Runs great. At Q8_0 it needs about 140 GB of 252 GB usable, with an estimated speed of 190 tok/s.

Best quant: Q8_0
Generation speed: 190 tok/s
Prompt processing: 8,862 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 256K

Best app to run it on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip

On Windows

vLLM

Inference server · runs on vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
On Windows it runs through WSL2.

vllm serve mistralai/Leanstral-2603

SGLang The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
Docker Model Runner Handy if you already work in Docker.

On Linux

vLLM

Inference server · runs on vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

vllm serve mistralai/Leanstral-2603

SGLang The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.
Docker Model Runner Handy if you already work in Docker.

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download Leanstral 119B-A6B

Original weights · Hugging Face

Full-precision files from Mistral AI, for fine-tuning, vLLM, Transformers.

huggingface.co/mistralai/Leanstral-2603 (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q8_0, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs great: How well it runs on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	33.3 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	12.8 / 15
Match score	86.1 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	61.1 GB	252 GB	279 tok/s	Runs great	51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q3_K_M`	71.9 GB	252 GB	262 tok/s	Runs great	62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q4_K_M`	86.2 GB	252 GB	243 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 79/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q5_K_M`	98.2 GB	252 GB	227 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 81/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q6_K`	111 GB	252 GB	214 tok/s	Runs great	73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	140 GB	252 GB	190 tok/s	Runs great	74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	252 GB	252 GB	128 tok/s	Runs welloffloads to RAM	74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

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 · 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 · 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 · 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 · 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 · 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 · 47.6 tok/s · Runs great

Quick answers

How much memory does Leanstral 119B-A6B need on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip 252GB?

At Q8_0 it needs about 140 GB. The NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip 252GB has 252 GB usable.

How fast is Leanstral 119B-A6B on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip 252GB?

About 190 tok/s at Q8_0, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Leanstral 119B-A6B should I use on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip 252GB?

Q8_0. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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.