Skip to content
Weights Not Walls
Menu

Qwen

Qwen2.5-Coder-3B-Instruct

Reviewed
Size
3.1B parameterscounted from the safetensors header on the Hub
Licence
custom, read it, Qwen Research License AgreementOur reading, check the licence: A custom licence we have not read for this model: other makers use the same name for different texts. Read the model's own licence file before you use it.Licence text
On the Hub since
6 Nov 2024the date the repo was created
Context length
32k tokensfrom the model's config
Fine-tune
of Qwen/Qwen2.5-Coder-3BQwen2ForCausalLM
On Hugging Face
Qwen/Qwen2.5-Coder-3B-Instruct387k downloads in the last 30 days, 157 likes

Scores

1 independent result on 1 eval set
GSM8KReported

Epoch's name: Qwen2.5-Coder-3B-Instruct. Best closed model on this set: gpt-4-0314, 92.0% (OpenAI). All 170 results

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

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: 0.28 GB, worked out from the model's config (Qwen/Qwen2.5-Coder-3B-Instruct), 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

Qwen/Qwen2.5-Coder-3B-Instruct-GGUF (the maker's own conversion), 96k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
Q2_K1.3 GBfile size2.1 GB1.3 + 0.28 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:Q2_K
Ollama
ollama run hf.co/Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:Q2_K
Download
hf download Qwen/Qwen2.5-Coder-3B-Instruct-GGUF --include "qwen2.5-coder-3b-instruct-q2_k.gguf" --local-dir Qwen2.5-Coder-3B-Instruct-GGUF
Q3_K_M1.6 GBfile size2.4 GB1.6 + 0.28 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:Q3_K_M
Ollama
ollama run hf.co/Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:Q3_K_M
Download
hf download Qwen/Qwen2.5-Coder-3B-Instruct-GGUF --include "qwen2.5-coder-3b-instruct-q3_k_m.gguf" --local-dir Qwen2.5-Coder-3B-Instruct-GGUF
Q4_01.9 GBfile size2.6 GB1.9 + 0.28 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:Q4_0
Ollama
ollama run hf.co/Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:Q4_0
Download
hf download Qwen/Qwen2.5-Coder-3B-Instruct-GGUF --include "qwen2.5-coder-3b-instruct-q4_0.gguf" --local-dir Qwen2.5-Coder-3B-Instruct-GGUF
Q4_K_M2.0 GBfile size2.7 GB2.0 + 0.28 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:Q4_K_M
Ollama
ollama run hf.co/Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:Q4_K_M
Download
hf download Qwen/Qwen2.5-Coder-3B-Instruct-GGUF --include "qwen2.5-coder-3b-instruct-q4_k_m.gguf" --local-dir Qwen2.5-Coder-3B-Instruct-GGUF
Q5_02.2 GBfile size3.0 GB2.2 + 0.28 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:Q5_0
Ollama
ollama run hf.co/Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:Q5_0
Download
hf download Qwen/Qwen2.5-Coder-3B-Instruct-GGUF --include "qwen2.5-coder-3b-instruct-q5_0.gguf" --local-dir Qwen2.5-Coder-3B-Instruct-GGUF
Q5_K_M2.3 GBfile size3.1 GB2.3 + 0.28 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:Q5_K_M
Ollama
ollama run hf.co/Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:Q5_K_M
Download
hf download Qwen/Qwen2.5-Coder-3B-Instruct-GGUF --include "qwen2.5-coder-3b-instruct-q5_k_m.gguf" --local-dir Qwen2.5-Coder-3B-Instruct-GGUF
Q6_K2.6 GBfile size3.4 GB2.6 + 0.28 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:Q6_K
Ollama
ollama run hf.co/Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:Q6_K
Download
hf download Qwen/Qwen2.5-Coder-3B-Instruct-GGUF --include "qwen2.5-coder-3b-instruct-q6_k.gguf" --local-dir Qwen2.5-Coder-3B-Instruct-GGUF
Q8_03.4 GBfile size4.1 GB3.4 + 0.28 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:Q8_0
Ollama
ollama run hf.co/Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:Q8_0
Download
hf download Qwen/Qwen2.5-Coder-3B-Instruct-GGUF --include "qwen2.5-coder-3b-instruct-q8_0.gguf" --local-dir Qwen2.5-Coder-3B-Instruct-GGUF
F166.3 GBfile size7.1 GB6.3 + 0.28 + 0.50
Commands
llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:F16
Ollama
ollama run hf.co/Qwen/Qwen2.5-Coder-3B-Instruct-GGUF:F16
Download
hf download Qwen/Qwen2.5-Coder-3B-Instruct-GGUF --include "qwen2.5-coder-3b-instruct-fp16.gguf" --local-dir Qwen2.5-Coder-3B-Instruct-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX 4bitlmstudio-community/Qwen2.5-Coder-3B-Instruct-MLX-4bit1.6 GBfile size2.4 GB1.6 + 0.28 + 0.50Download page
MLX 4bitmlx-community/Qwen2.5-Coder-3B-Instruct-4bit1.6 GBfile size2.4 GB1.6 + 0.28 + 0.50Download page

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

FormatSizeMemory neededRepo
BF16original weights5.7 GBfile size6.5 GB5.7 + 0.28 + 0.50
hf download Qwen/Qwen2.5-Coder-3B-Instruct --local-dir Qwen2.5-Coder-3B-Instruct
Other conversions (8; sizes not read)

The Hub tags 100 or more 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.