Skip to content
Weights Not Walls
Menu

Qwen

Qwen3-4B-Instruct-2507

Reviewed
Size
4.0B parameterscounted from the safetensors header on the Hub
Licence
custom, read it, Apache License 2.0Our 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
5 Aug 2025the date the repo was created
Context length
256k tokensfrom the model's config
Kind
Base model (no base model declared on the Hub)Qwen3ForCausalLM
On Hugging Face
Qwen/Qwen3-4B-Instruct-25072.7M downloads in the last 30 days, 1.1k likes

Scores

2 independent results on 2 eval sets
GPQA diamondRe-run by Epoch AI
  • default setting45.8%±2.928 Aug 2026, log

Epoch's name: qwen3-4b-instruct-2507. Best closed model on this set: gpt-6.2-astra_max, 96.8% (OpenAI). All 341 results

OTIS Mock AIME 2024-2025Re-run by Epoch AI
  • default setting52.2%±6.628 Aug 2026, log

Epoch's name: qwen3-4b-instruct-2507. Best closed model on this set: claude-fable-5_high, 100.0% (Anthropic). All 318 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: 1.1 GB, worked out from the model's config (Qwen/Qwen3-4B-Instruct-2507), 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

unsloth/Qwen3-4B-Instruct-2507-GGUF (converted by unsloth), 904k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
UD-IQ3_XXS1.6 GBfile size3.2 GB1.6 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-IQ3_XXS
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-IQ3_XXS
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-UD-IQ3_XXS.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
Q3_K_S1.8 GBfile size3.4 GB1.8 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q3_K_S
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q3_K_S
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q3_K_S.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
Q3_K_M1.9 GBfile size3.6 GB1.9 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q3_K_M
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q3_K_M
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q3_K_M.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
UD-Q3_K_XL2.0 GBfile size3.6 GB2.0 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q3_K_XL
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q3_K_XL
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-UD-Q3_K_XL.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
IQ4_XS2.1 GBfile size3.7 GB2.1 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:IQ4_XS
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:IQ4_XS
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-IQ4_XS.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
Q4_02.2 GBfile size3.8 GB2.2 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_0
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_0
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q4_0.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
IQ4_NL2.2 GBfile size3.8 GB2.2 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:IQ4_NL
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:IQ4_NL
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-IQ4_NL.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
Q4_K_S2.2 GBfile size3.8 GB2.2 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_K_S
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_K_S
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q4_K_S.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
Q4_K_M2.3 GBfile size4.0 GB2.3 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_K_M
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_K_M
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q4_K_M.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
UD-Q4_K_XL2.4 GBfile size4.0 GB2.4 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q4_K_XL
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q4_K_XL
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-UD-Q4_K_XL.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
Q4_12.4 GBfile size4.0 GB2.4 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_1
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_1
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q4_1.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
Q5_K_S2.6 GBfile size4.3 GB2.6 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q5_K_S
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q5_K_S
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q5_K_S.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
Q5_K_M2.7 GBfile size4.3 GB2.7 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q5_K_M
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q5_K_M
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q5_K_M.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
UD-Q5_K_XL2.7 GBfile size4.3 GB2.7 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q5_K_XL
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q5_K_XL
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-UD-Q5_K_XL.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
Q6_K3.1 GBfile size4.7 GB3.1 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q6_K
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q6_K
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q6_K.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
UD-Q6_K_XL3.4 GBfile size5.0 GB3.4 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q6_K_XL
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q6_K_XL
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-UD-Q6_K_XL.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
Q8_04.0 GBfile size5.6 GB4.0 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q8_0
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q8_0
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-Q8_0.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
UD-Q8_K_XL4.7 GBfile size6.3 GB4.7 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q8_K_XL
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:UD-Q8_K_XL
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-UD-Q8_K_XL.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF
F167.5 GBfile size9.1 GB7.5 + 1.1 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:F16
Ollama
ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:F16
Download
hf download unsloth/Qwen3-4B-Instruct-2507-GGUF --include "Qwen3-4B-Instruct-2507-F16.gguf" --local-dir Qwen3-4B-Instruct-2507-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLX 4bitmlx-community/Qwen3-4B-Instruct-2507-4bit2.1 GBfile size3.7 GB2.1 + 1.1 + 0.50Download page
MLX 4bitlmstudio-community/Qwen3-4B-Instruct-2507-MLX-4bit2.1 GBfile size3.7 GB2.1 + 1.1 + 0.50Download page

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

FormatSizeMemory neededRepo
BF16original weights7.5 GBfile size9.1 GB7.5 + 1.1 + 0.50
hf download Qwen/Qwen3-4B-Instruct-2507 --local-dir Qwen3-4B-Instruct-2507
Other conversions (16; 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.