Skip to content
Weights Not Walls
Menu

bigcode

starcoder2-15b

Reviewed
Size
16.0B parameterscounted from the safetensors header on the Hub
Licence
unknown, BigCode OpenRAIL-MOur reading, check the licence: A responsible AI licence: commercial use is allowed, but the licence lists uses that are not allowed, and you must pass those use restrictions on to anyone you give the model or a changed version to.
On the Hub since
20 Feb 2024the date the repo was created
Context length
16k tokensfrom the model's config
Kind
Base model (no base model declared on the Hub)Starcoder2ForCausalLM
On Hugging Face
bigcode/starcoder2-15b14k downloads in the last 30 days, 684 likes

Scores

4 independent results on 4 eval sets
ARC AI2Reported

Epoch's name: starcoder2-15b. Best closed model on this set: gpt-3.5-turbo-1106, 87.4% (OpenAI). All 134 results

GSM8KReported

Epoch's name: starcoder2-15b. Best closed model on this set: gpt-4-0314, 92.0% (OpenAI). All 170 results

MMLUReported

Epoch's name: starcoder2-15b. Best closed model on this set: gpt-4o-2024-11-20, 88.1% (OpenAI). All 217 results

WinograndeReported

Epoch's name: starcoder2-15b. Best closed model on this set: claude-3-opus-20240229, 88.5% (Anthropic). All 137 results

Claimed by the maker Claimed

  • CruxEval-I pass@148.1
  • DS-1000 pass@133.8
  • GSM8K (PAL) accuracy65.1
  • HumanEval+ pass@137.8
  • HumanEval pass@146.3
  • RepoBench-v1.1 edit-smiliarity74.08

Values as the card gives them, unscaled. Source: the model card on the Hugging Face Hub. Claimed scores are never mixed with independent ones.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.

Run it yourself

file sizes read from the Hub 19 Nov 2026

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.63 GB, worked out from the model's config (bigcode/starcoder2-15b), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

GGUF for llama.cpp, Ollama, LM Studio and others

second-state/StarCoder2-15B-GGUF (converted by second-state), 2.9k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
Q2_K5.8 GBfile size6.9 GB5.8 + 0.63 + 0.50
Commands
llama.cpp
llama-server -hf second-state/StarCoder2-15B-GGUF:Q2_K
Ollama
ollama run hf.co/second-state/StarCoder2-15B-GGUF:Q2_K
Download
hf download second-state/StarCoder2-15B-GGUF --include "starcoder2-15b-Q2_K.gguf" --local-dir StarCoder2-15B-GGUF
Q3_K_S6.5 GBfile size7.6 GB6.5 + 0.63 + 0.50
Commands
llama.cpp
llama-server -hf second-state/StarCoder2-15B-GGUF:Q3_K_S
Ollama
ollama run hf.co/second-state/StarCoder2-15B-GGUF:Q3_K_S
Download
hf download second-state/StarCoder2-15B-GGUF --include "starcoder2-15b-Q3_K_S.gguf" --local-dir StarCoder2-15B-GGUF
Q3_K_M7.5 GBfile size8.7 GB7.5 + 0.63 + 0.50
Commands
llama.cpp
llama-server -hf second-state/StarCoder2-15B-GGUF:Q3_K_M
Ollama
ollama run hf.co/second-state/StarCoder2-15B-GGUF:Q3_K_M
Download
hf download second-state/StarCoder2-15B-GGUF --include "starcoder2-15b-Q3_K_M.gguf" --local-dir StarCoder2-15B-GGUF
Q3_K_L8.3 GBfile size9.5 GB8.3 + 0.63 + 0.50
Commands
llama.cpp
llama-server -hf second-state/StarCoder2-15B-GGUF:Q3_K_L
Ollama
ollama run hf.co/second-state/StarCoder2-15B-GGUF:Q3_K_L
Download
hf download second-state/StarCoder2-15B-GGUF --include "starcoder2-15b-Q3_K_L.gguf" --local-dir StarCoder2-15B-GGUF
Q4_08.4 GBfile size9.6 GB8.4 + 0.63 + 0.50
Commands
llama.cpp
llama-server -hf second-state/StarCoder2-15B-GGUF:Q4_0
Ollama
ollama run hf.co/second-state/StarCoder2-15B-GGUF:Q4_0
Download
hf download second-state/StarCoder2-15B-GGUF --include "starcoder2-15b-Q4_0.gguf" --local-dir StarCoder2-15B-GGUF
Q4_K_S8.6 GBfile size9.7 GB8.6 + 0.63 + 0.50
Commands
llama.cpp
llama-server -hf second-state/StarCoder2-15B-GGUF:Q4_K_S
Ollama
ollama run hf.co/second-state/StarCoder2-15B-GGUF:Q4_K_S
Download
hf download second-state/StarCoder2-15B-GGUF --include "starcoder2-15b-Q4_K_S.gguf" --local-dir StarCoder2-15B-GGUF
Q4_K_M9.2 GBfile size10.3 GB9.2 + 0.63 + 0.50
Commands
llama.cpp
llama-server -hf second-state/StarCoder2-15B-GGUF:Q4_K_M
Ollama
ollama run hf.co/second-state/StarCoder2-15B-GGUF:Q4_K_M
Download
hf download second-state/StarCoder2-15B-GGUF --include "starcoder2-15b-Q4_K_M.gguf" --local-dir StarCoder2-15B-GGUF
Q5_010.3 GBfile size11.4 GB10.3 + 0.63 + 0.50
Commands
llama.cpp
llama-server -hf second-state/StarCoder2-15B-GGUF:Q5_0
Ollama
ollama run hf.co/second-state/StarCoder2-15B-GGUF:Q5_0
Download
hf download second-state/StarCoder2-15B-GGUF --include "starcoder2-15b-Q5_0.gguf" --local-dir StarCoder2-15B-GGUF
Q5_K_S10.3 GBfile size11.4 GB10.3 + 0.63 + 0.50
Commands
llama.cpp
llama-server -hf second-state/StarCoder2-15B-GGUF:Q5_K_S
Ollama
ollama run hf.co/second-state/StarCoder2-15B-GGUF:Q5_K_S
Download
hf download second-state/StarCoder2-15B-GGUF --include "starcoder2-15b-Q5_K_S.gguf" --local-dir StarCoder2-15B-GGUF
Q5_K_M10.6 GBfile size11.8 GB10.6 + 0.63 + 0.50
Commands
llama.cpp
llama-server -hf second-state/StarCoder2-15B-GGUF:Q5_K_M
Ollama
ollama run hf.co/second-state/StarCoder2-15B-GGUF:Q5_K_M
Download
hf download second-state/StarCoder2-15B-GGUF --include "starcoder2-15b-Q5_K_M.gguf" --local-dir StarCoder2-15B-GGUF
Q6_K12.2 GBfile size13.3 GB12.2 + 0.63 + 0.50
Commands
llama.cpp
llama-server -hf second-state/StarCoder2-15B-GGUF:Q6_K
Ollama
ollama run hf.co/second-state/StarCoder2-15B-GGUF:Q6_K
Download
hf download second-state/StarCoder2-15B-GGUF --include "starcoder2-15b-Q6_K.gguf" --local-dir StarCoder2-15B-GGUF
Q8_015.8 GBfile size16.9 GB15.8 + 0.63 + 0.50
Commands
llama.cpp
llama-server -hf second-state/StarCoder2-15B-GGUF:Q8_0
Ollama
ollama run hf.co/second-state/StarCoder2-15B-GGUF:Q8_0
Download
hf download second-state/StarCoder2-15B-GGUF --include "starcoder2-15b-Q8_0.gguf" --local-dir StarCoder2-15B-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX 4bitmlx-community/bigcode-starcoder2-15b-4bit8.4 GBfile size9.5 GB8.4 + 0.63 + 0.50Download page
MLX 8bitmlx-community/bigcode-starcoder2-15b-8bit15.8 GBfile size16.9 GB15.8 + 0.63 + 0.50Download page

Original weights size from the safetensors header, for vLLM, SGLang, Transformers

FormatSizeMemory neededRepo
F32original weights59.4 GBfile size60.6 GB59.4 + 0.63 + 0.50
hf download bigcode/starcoder2-15b --local-dir starcoder2-15b
Other conversions (4; sizes not read)

The Hub tags 22 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Fine-tunes of this model

from our snapshot of the Hub

Repos that declare this model as their base, most downloaded first. Listing is not a recommendation; unreviewed ones have not been checked.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.