Can the NVIDIA L40S run LLaVA 1.6 Mistral 7B?

Yes, it runs great

Runs great. At Q8_0 it needs about 12.1 GB of 48.0 GB usable, with an estimated speed of 71.3 tok/s.

Best quant: Q8_0
Generation speed: 71.3 tok/s
Prompt processing: 8,712 tok/s
First token (1K prompt): 0.3 s
Largest safe context: 32K

Best app to run it on the NVIDIA L40S

On Linux

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 llava-hf/llava-v1.6-mistral-7b-hf

Ollama One command with Ollama’s own build of this model.
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.

On Windows

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

One command with Ollama’s own build of this model.
Serves an OpenAI-compatible API that other apps and coding tools can use.

ollama run llava:7b-v1.6-mistral-q8_0

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.
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.

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 LLaVA 1.6 Mistral 7B

Recommended for the NVIDIA L40S: Q8_0. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run llava:7b-v1.6-mistral-q8_0

Original weights · Hugging Face

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

huggingface.co/llava-hf/llava-v1.6-mistral-7b-hf (opens in a new tab)

No sign-in needed.

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (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 L40S: 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.	12.6 / 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.	5.8 / 15
Match score	58.4 / 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 L40S

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	7.1 GB	48.0 GB	230 tok/s	Runs great	19Basic quality (D) · 19 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking.
`Q3_K_M`	7.8 GB	48.0 GB	181 tok/s	Runs great	23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking.
`Q4_K_M`	8.7 GB	48.0 GB	140 tok/s	Runs great	26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.
`Q5_K_M`	9.4 GB	48.0 GB	116 tok/s	Runs great	27Basic quality (D) · 27 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.
`Q6_K`	10.3 GB	48.0 GB	97.2 tok/s	Runs great	27Basic quality (D) · 27 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.
`Q8_0`	12.1 GB	48.0 GB	71.3 tok/s	Runs great	28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.
`F16`	19.2 GB	48.0 GB	32.9 tok/s	Runs great	28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (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

28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q8_0 · 45.5 tok/s · Runs great
28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q8_0 · 55.5 tok/s · Runs great
28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q8_0 · 60.8 tok/s · Runs great
28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q8_0 · 74.0 tok/s · Runs great
28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Q8_0 · 79.2 tok/s · Runs great
27Basic quality (D) · 27 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3060 12GB Q6_K · 40.5 tok/s · Runs great

Quick answers

How much memory does LLaVA 1.6 Mistral 7B need on the NVIDIA L40S 48GB?

At Q8_0 it needs about 12.1 GB. The NVIDIA L40S 48GB has 48.0 GB usable.

How fast is LLaVA 1.6 Mistral 7B on the NVIDIA L40S 48GB?

About 71.3 tok/s at Q8_0, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of LLaVA 1.6 Mistral 7B should I use on the NVIDIA L40S 48GB?

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.