on

Can the NVIDIA L40 run Yi 6B Chat?

20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.

Yes, it runs great

Runs great. At F16 it needs about 15.4 GB of 48.0 GB usable, with an estimated speed of 41.1 tok/s.

Best quant
F16
Generation speed
41.1 tok/s
Prompt processing
10,752 tok/s
First token (1K prompt)
0.3 s
Largest safe context
4K

Best app to run it on the NVIDIA L40

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 01-ai/Yi-6B-Chat
  • Ollama One command with Ollama’s own build of this model.
  • LM Studio Point-and-click: search, download and chat in one window.

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 yi:6b-chat-fp16
  • LM Studio Point-and-click: search, download and chat in one window.
  • llama.cpp Usually the first to support new model architectures.

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 Yi 6B Chat

Recommended for the NVIDIA L40: F16. 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 yi:6b-chat-fp16

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the F16 file (opens in a new tab)

huggingface.co/mradermacher/Yi-6B-Chat-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/Yi-6B-Chat-GGUF:F16

Original weights · Hugging Face

Full-precision files from 01.AI, for fine-tuning, vLLM, Transformers.

huggingface.co/01-ai/Yi-6B-Chat (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 20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking.
How capable the model itself is at F16, 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 L40: 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.9.0 / 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.7.4 / 15
Match score56.4 / 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 L40

Quant Memory needed Available Speed Runs Quality Download
Q2_K 5.7 GB 48.0 GB 287 tok/s Runs great 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q3_K_M 6.2 GB 48.0 GB 226 tok/s Runs great 16Basic quality (D) · 16 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q4_K_M 7.0 GB 48.0 GB 175 tok/s Runs great 19Basic quality (D) · 19 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q5_K_M 7.6 GB 48.0 GB 145 tok/s Runs great 19Basic quality (D) · 19 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q6_K 8.2 GB 48.0 GB 121 tok/s Runs great 19Basic quality (D) · 19 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
Q8_0 9.7 GB 48.0 GB 89.1 tok/s Runs great 20Basic quality (D) · 20 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab)
F16 15.4 GB 48.0 GB 41.1 tok/s Runs great 20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 4K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

Quick answers

How much memory does Yi 6B Chat need on the NVIDIA L40 48GB?

At F16 it needs about 15.4 GB. The NVIDIA L40 48GB has 48.0 GB usable.

How fast is Yi 6B Chat on the NVIDIA L40 48GB?

About 41.1 tok/s at F16, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Yi 6B Chat should I use on the NVIDIA L40 48GB?

F16. 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.

Was this page helpful?