whatmodel.sh / Llama 2 13B Chat

Llama 2 13B Chat

+ contribute

Llama 2 13B Chat is an open-weights language model from Meta, released July 2023. Its published size is 13.02B parameters and a 4k-token context window. Licence: llama2.

Catalogue identity notes

Comparison model from the Epoch AI internal-evaluation CSVs (Epoch release date 2023-07-18). Chat checkpoint Llama-2-13b-chat. 13,015,866,880 parameters (safetensors metadata of the -hf repo).

33.4±0.9#614 of 719 LLMsfrom 28 benchmark results across 15 sources

$ how it compares

The LLMs ranked either side of Llama 2 13B Chat, out of 828 with a score, then more from Meta.

#	model	score	where	RAM	released
708	PaLM 2 Chat (chat-bison@001) Google	34±2	comparison only		2023-05
709	Qwen3 0.6B Alibaba	33±1	local	~1.8GB	2025-04
710	Llama 2 13B Chat Meta	33±1	local	~9.8GB	2023-07
711	Flan-T5 XXL Google	33±1	local	~49GB	2022-10
712	StarCoder2 3B BigCode	33±1	local	~3.4GB	2024-02
	more from Meta
24	Muse Spark 1.3 Meta	77±1	api $2.00/M		2026-09
40	Muse Spark 1.2 Meta	75±1	api $2.00/M		2026-08
43	Muse Spark 1.1 Meta	75±1	api $2.00/M		2026-07

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▃▃▆██▇▆▄▃▁ #446 of 458 * · 5.4% of its score · 1 test

Beats Molmo 7B-D (0924), DeepSeek R1 Distill Qwen 1.5B, Qwen3 0.6B here, though they rank higher overall. Trails Falcon3 1B Instruct, Gemma 2B IT, Granite 3.0 1B-A400M Instruct here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Tulu 2: CodexEval pass@10	33.1% ✎	▃▃▃·▆▃▃█▃▂▂▅ beats 3/25	very easy · avg 86%	▇▇ 5.4%	sharp · at its level

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #359 of 393 · 34% of its score · 6 tests

Beats Gemma 4 E2B, Code Llama 70B Instruct, Code Llama 34B Instruct here, though they rank higher overall. Trails Gemma 3 270M IT, SmolLM2 360M Instruct, Granite 4.0 350M here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
AlpacaEval 2 length-controlled	8.4% ✎	▁▂▂▃▆▆█▆▄▄▁▁ beats 18/122	medium · avg 39%	▇▇▇▇ 10%	typical
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)	1081.0 ✎	▂▁▂▁▃▇█▆▇▄▂▂ beats 38/95	avg 1201	▇▇▇ 6.6%	blunt
LMArena (text)	1141.4 ✎	▁▁▁▃▃▃▃▆▆▇█▃ beats 33/379	avg 1268	▇▇▇ 6.5%	blunt
MT-Bench (GPT-4 single-answer grading, LMSYS runs)	6.6500 MT-Bench score (1-10) ✎	▆▂▂▆▆▄██▂▄▄▆ beats 19/28	avg 8.819 MT-Bench score (1-10)	▇▇ 5.7%	sharp · noisy
AlpacaEval 1.0 win rate (vs text-davinci-003, GPT-4 judge)	81.1% ✎	▂▂·▆·▇▃▆█▆▄▂ beats 19/45	very easy · avg 96%	▇ 3.3%	sharp · at its level · noisy
Arabic IFEval prompt-level (Inception)	2.0% ✎	▁·▃▁▂▁▄▄▆▄█▄ beats 1/38	medium · avg 49%	▇ 2.4%	sharp

math▃▂▃▅▆▅▄█▄▁▁▁ #394 of 398 * · 7.0% of its score · 1 test

Trails Qwen2 0.5B Instruct, Granite 4.0 350M, Granite 4.0 H 350M here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
GSM8K +1	9.0% ✎	▆▂▅█▅▅▃▆···▂ beats 0/25	easy · avg 82%	▇▇▇ 7.0%	sharp · at its level · several runs

other tests17 not in a task · 53% of its score

test	result	vs the others in its run	difficulty	counts	why
BIG-Bench Hard +1	40.3% ✎	▁·····▃█▂▅·▁ beats 3/25	easy · avg 77%	▇▇▇▇▇ 13%	sharp · several runs
Natural Questions (closed book)	27.3% ✎	▁·▁·▁▂▁▂·▅▂█ beats 24/28	medium · avg 58%	▇▇▇▇ 9.3%	typical
MMLU +1	53.2% ✎	▁▁▃▃▄█▄▁█··▁ beats 13/25	easy · avg 74%	▇▇▇ 6.4%	at its level · several runs
ARC Challenge	61.2% ✎	▆▁▁▂▂▅▇█▄▃▃▂ beats 73/97	easy · avg 86%	▇▇ 5.0%	sharp · at its level
AGIEval English	38.9% ✎	█▄▄··▄··▄█·█ beats 1/9	easy · avg 69%	▇ 3.1%	at its level
Open Persian LLM Leaderboard v2 average (21 tasks)	29.4% ✎	▃▄▂▃█▄▃▆▃▅▂▂ beats 0/81	medium · avg 58%	▇ 2.7%	blunt · at its level
EQ-Bench v1 (60 questions, paper run)	33.0% ✎	▂··▄·▃▆▄▂█·▂ beats 3/14	medium · avg 57%	▇ 2.6%	at its level
BRIDGE clinical text, zero-shot average (87 tasks)	20.9% ✎	▁▁▁▁▁▃▂▃▄▆█▃ beats 13/97	hard · avg 32%	▇ 2.3%	blunt

9 more tests

test	result	vs the others in its run	difficulty	counts	why
ARC Easy	76.3% ✎	▁▂▃▂▃▅▇█▇▆▄▆ beats 55/65	easy · avg 88%	▇ 1.7%	at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)	58.0% ✎	▃▁▁▁▁▁▁▁▃█▅▁ beats 84/276	medium · avg 73%	▇ 1.2%	at its level · noisy
TriviaQA	9.8% ✎	▁··▁█▃▃▁▄▅▄█ beats 7/28	easy · avg 79%	▇ 1.2%	at its level · noisy
Tulu 2: TyDiQA gold passage, 1-shot F1	32.1% ✎	▂··▃▃▂▂▂█▅▁▂ beats 2/25	medium · avg 61%	▇ 1.1%	blunt · at its level
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy	57.6% ✎	▁▁▁▁▁▁▁▃▄█▄▃ beats 30/146	easy · avg 83%	▇ 1.0%	at its level · noisy
Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate)	89.5% ✎	▁▁▂▃▄▄█▆▃▂▂▁ beats 23/140	very easy · avg 94%	▇ 0.8%	blunt · noisy
HaluEval QA hallucination detection (accuracy)	57.3% ✎	█▁▁·▁▁·▁▃▁▁▁ beats 22/27	medium · avg 70%	▇ 0.6%	sharp · noisy
TruthfulQA MC2	44.0% ✎	▅▃█▆▁▂▅···▁▁ beats 16/31	medium · avg 64%	▇ 0.5%	blunt · at its level
Chess Puzzles (Epoch)	0.0% ✎	█▁▁▁▁▂▁▄▂▂▁▁ beats 9/135	very hard · avg 5.9%	▇ 0.0%	sharp · too hard for it · noisy

$ 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 Llama 2 13B Chat · needs ~7.9 GB · from huggingface.co/TheBloke
chat in the terminal
llama cli -hf TheBloke/Llama-2-13B-chat-GGUF:Q4_K_M
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf TheBloke/Llama-2-13B-chat-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 Llama 2 13B Chat · needs ~7.9 GB · from huggingface.co/TheBloke
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/TheBloke/Llama-2-13B-chat-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 Llama 2 13B Chat · needs ~8.31 GB · from ollama.com
chat in the terminal
ollama run llama2:13b-chat

Weights and documentation: huggingface.co/meta-llama ↗

$ how the score was worked out · Orca 2: Teaching Small Langua… 23%, Tulu 2 — base and instruction… 20%, AlpacaEval 1.0 and 2.0 leader… 13% and 12 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
Orca 2: Teaching Small Language Models How to Reason (Mitra et al., Microsoft)	6	▇▇▇▇▇▇▇ 23%	CC BY 4.0
Tulu 2 — base and instruction-tuned evaluations	5	▇▇▇▇▇▇ 20%	CC BY 4.0
AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)	2	▇▇▇▇ 13%	Apache-2.0
Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)	4	▇▇▇ 12%	Apache-2.0
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)	1	▇▇ 7%	CC-BY-4.0
LMArena leaderboard dataset	1	▇▇ 6%	CC BY 4.0
LMSYS Chatbot Arena leaderboard Space: MT-Bench column of the published leaderboard table	1	▇▇ 6%	Apache-2.0
Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)	1	▇ 3%	Apache-2.0
EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models — authors' own runs	1	▇ 3%	CC BY 4.0
Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)	1	▇ 2%	Apache-2.0
BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)	1	▇ 2%	MIT
Open Portuguese LLM Leaderboard (archived)	1	▇ 1%	Apache-2.0
EuroEval leaderboards (results collection), English generative leaderboard	1	▇ 1%	MIT
Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)	1	▇ 1%	Apache-2.0
Epoch AI — internal evaluations	1	▇ 0%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 33.4