whatmodel.sh / DeepSeek-Coder 33B Base

DeepSeek-Coder 33B Base

+ contribute

DeepSeek-Coder 33B Base is an open-weights language model from DeepSeek, released October 2023. Its published size is 33.34B parameters and a 16k-token context window. Licence: deepseek.

Catalogue identity notes

Maker repo deepseek-ai/deepseek-coder-33b-base @45c85ca: licence tag other (deepseek-license). 33,342,991,360 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2023-10: month the maker's Hugging Face repo was created (createdAt 2023-10-28). DeepSeek-Coder v1 base model. Ollama tags deepseek-coder:33b-base-q4_K_M, deepseek-coder:33b-base-q8_0 (sizes as listed on the tags page, observed 2026-09-29).

40.9±0.6#516 of 719 LLMsfrom 11 benchmark results across 5 sources

$ how it compares

The LLMs ranked either side of DeepSeek-Coder 33B Base, out of 828 with a score, then more from DeepSeek.

#	model	score	where	RAM	released
606	Code Llama 34B Python Meta	41±1	local	~23GB	2023-08
607	speechless-coding-7b-16k-tora uukuguy	41±1	local	~16GB	2023-10
608	DeepSeek-Coder 33B Base DeepSeek	41±1	local	~22GB	2023-10
609	InternLM2 Chat 20B Shanghai AI Laboratory (InternLM)	41±1	local	~14GB	2024-01
610	DeepSeek LLM 67B Chat DeepSeek	41±1	local	~31GB	2023-11
	more from DeepSeek
21	DeepSeek V4.1 Flash DeepSeek	78±1	api $0.26/M +local	~537GB	2026-09
31	DeepSeek V4 Pro (0813) DeepSeek	76±1	api $1.63/M +local	~1010GB	2026-08
35	DeepSeek V3.2 Speciale DeepSeek	76±3	comparison only

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #368 of 458 · 85% of its score · 6 tests

Beats LFM2.5 8B-A1B, Qwen3-VL 2B Thinking, DeepSeek R1 Distill Qwen 7B here, though they rank higher overall. Trails Qwen2.5 1.5B Instruct, WizardLM 13B V1.2, Granite 3.0 2B Instruct here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
HumanEval +2	51.2% ✎	▁·▁▁▃▄▆▅█▃▁▁ beats 36/99	easy · avg 79%	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 55%	sharp · at its level · several runs
HumanEval+	44.5% ✎	▁·▁▁▁▃▄▄▄█▃▁ beats 36/99	easy · avg 74%	▇▇▇▇▇▇▇▇▇ 21%	sharp · at its level
DS-1000	40.2% ✎	▄▄·▄██▄█·█·▄ beats 12/12	medium · avg 52%	▇ 3.6%	at its level
MBPP	73.2% ✎	▄▄▄██▄·▄█·▄▄ beats 12/12	easy · avg 82%	▇ 3.4%	at its level
CRUXEval-I	46.5% ✎	▁··▁▅▂█▇▁··▁ beats 18/22	medium · avg 54%	▇ 1.2%	at its level
CRUXEval-O	48.6% ✎	▁·▂▃▁█▁▃···▁ beats 19/22	medium · avg 53%	▇ 1.1%	blunt · at its level

math▁▂▃▅▆▅▄█▄▁▁▁ #307 of 398 * · 2.2% of its score · 1 test

Beats GPT-4 (0613), Athene-70B, Llama 3 70B Instruct here, though they rank higher overall. Trails Gemma 7B (base), DeepSeek R1 Distill Qwen 1.5B, Phi-3.5-vision-instruct here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
GSM8K	58.7% ✎	▄▄▄·▄█·██·█▄ beats 11/12	easy · avg 75%	▇ 2.2%	sharp · at its level

other tests2 not in a task · 12% of its score

test	result	vs the others in its run	difficulty	counts	why
EvoEval (overall)	36.8% ✎	▂▂▃▄▄█▃▄▅▃▁▃ beats 25/42	medium · avg 55%	▇▇▇ 8.7%	at its level
BigCodeBench (Complete)	46.6% ✎	▂▁▁▄▂▅▇█▆▂▂▂ beats 45/58	medium · avg 50%	▇ 3.4%	at its level

$ where to run it

llama.cpp · recommended

version

Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
macOS / Linux
curl -LsSf https://llama.app/install.sh | sh
Windows
irm https://llama.app/install.ps1 | iex
other ways to install ↗
Run DeepSeek-Coder 33B Base · needs ~19.9 GB · from huggingface.co/TheBloke
chat in the terminal
llama cli -hf TheBloke/deepseek-coder-33B-base-GGUF:Q4_K_M
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf TheBloke/deepseek-coder-33B-base-GGUF:Q4_K_M

LM Studio

version

Install LM Studio · Open the app once before using the lms command.
download it (macOS / Windows / Linux) ↗
Run DeepSeek-Coder 33B Base · needs ~19.9 GB · from huggingface.co/TheBloke
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/TheBloke/deepseek-coder-33B-base-GGUF@Q4_K_M -y
Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

Install Ollama
download it (macOS / Windows) ↗
Linux
curl -fsSL https://ollama.com/install.sh | sh
Run DeepSeek-Coder 33B Base · needs ~20 GB · from ollama.com
chat in the terminal
ollama run deepseek-coder:33b-base-q4_K_M

Weights and documentation: huggingface.co/deepseek-ai ↗

$ how the score was worked out · EvalPlus / EvalPerf published… 51%, Top Leaderboard Ranking = Top… 24%, StarCoder 2 and The Stack v2:… 19% and 2 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

source	results	share of the score	licence
EvalPlus / EvalPerf published evaluation runs	2	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 51%	Apache-2.0
Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runs	2	▇▇▇▇▇▇▇ 24%	CC BY 4.0
StarCoder 2 and The Stack v2: The Next Generation — authors' own runs	4	▇▇▇▇▇▇ 19%	CC BY-SA 4.0
BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4	1	▇ 3%	CC BY 4.0
CRUXEval published evaluation results (authors' generations and scores)	2	▇ 2%	MIT
prior · pull toward the middle		▇ 0%
weighted average		= 40.9

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated 2026-10-11 02:20 UTC · sources and licences · json