DeepSeek Coder 33B Instruct on NVIDIA L4

Can the NVIDIA L4 run DeepSeek Coder 33B Instruct?

Yes, it runs well

Runs well. At Q3_K_M it needs about 20.2 GB of 24.0 GB usable, with an estimated speed of 14.3 tok/s.

Best quant: Q3_K_M
Generation speed: 14.3 tok/s
Prompt processing: 654 tok/s
First token (1K prompt): 1.6 s
Largest safe context: 16K

Best app to run it on the NVIDIA L4

On Linux

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 deepseek-coder:33b-instruct-q3_K_M

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

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 deepseek-coder:33b-instruct-q3_K_M

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

Want an agent? DeepSeek Coder 33B Instruct supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

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 DeepSeek Coder 33B Instruct

Recommended for the NVIDIA L4: Q3_K_M. 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 deepseek-coder:33b-instruct-q3_K_M

Quantized files · GGUF

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

Download the Q3_K_M file (opens in a new tab)

huggingface.co/TheBloke/deepseek-coder-33B-instruct-GGUF (opens in a new tab)

ollama run hf.co/TheBloke/deepseek-coder-33B-instruct-GGUF:Q3_K_M

Original weights · Hugging Face

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

huggingface.co/deepseek-ai/deepseek-coder-33b-instruct (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from DeepSeek. The weights themselves download from Hugging Face.

github.com/deepseek-ai/DeepSeek-Coder (opens in a new tab)

git clone https://github.com/deepseek-ai/DeepSeek-Coder

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

How it’s rated

Quality 36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q3_K_M, 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 well: How well it runs on the NVIDIA L4: 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.	16.6 / 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.	9.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	65.6 / 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 L4

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	17.2 GB	24.0 GB	18.1 tok/s	Runs well	30Basic quality (D) · 30 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.	GGUF (opens in a new tab)
`Q3_K_M`	20.2 GB	24.0 GB	14.3 tok/s	Runs well	36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	24.2 GB	24.0 GB	10.6 tok/s	Runs welloffloads to RAM	41Fair quality (C) · 41 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`	27.6 GB	24.0 GB	6.0 tok/s	Slowoffloads to RAM	42Fair quality (C) · 42 of 100: how capable the model is at Q5_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)
`Q6_K`	31.2 GB	24.0 GB	4.0 tok/s	Slowoffloads to RAM	43Fair quality (C) · 43 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	39.2 GB	24.0 GB	2.2 tok/s	Very slowheavy RAM offload	44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	70.6 GB	24.0 GB	—	Won't run	44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 5/100 (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

41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q4_K_M · 66.0 tok/s · Runs great
36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q3_K_M · 44.6 tok/s · Runs great
36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q3_K_M · 48.0 tok/s · Runs great
36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q3_K_M · 39.3 tok/s · Runs great
43Fair quality (C) · 43 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 RTX PRO 6000 Blackwell Q6_K · 45.8 tok/s · Runs great
41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (64 GB) Q4_K_M · 17.3 tok/s · Runs well

Quick answers

How much memory does DeepSeek Coder 33B Instruct need on the NVIDIA L4 24GB?

At Q3_K_M it needs about 20.2 GB. The NVIDIA L4 24GB has 24.0 GB usable.

How fast is DeepSeek Coder 33B Instruct on the NVIDIA L4 24GB?

About 14.3 tok/s at Q3_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of DeepSeek Coder 33B Instruct should I use on the NVIDIA L4 24GB?

Q3_K_M. 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.