Skip to content
Local AI Wizard
Your machine
Theme

Qwen3 4B Instruct 2507

Alibaba · Qwen/Qwen3-4B-Instruct-2507

Q4 file 2.5 GB (Q4_K_M) · runs well from 8 GB · Weights license: Apache 2.0

Measured speed134.5 tok/sMLX q4 · 1 machine · mlx-lm BENCHMARKS.md · all rows
Memory needed~3 GBQ4 weights + working room, before the machine's reserve
Parameters4 Bmanufacturer specification
Context262,144 tokensPublished for this model

Quality

No result in LiveBench 2026-06-25, LMArena 2026-10-22 Not in LiveBench 2026-06-25 or LMArena 2026-10-22

Reported by the publisher

25 results · Alibaba's model card · read 2026-10-25
MMLU-Pro
69.6Knowledge
MMLU-Redux
84.2Knowledge
GPQA
62.0Knowledge
SuperGPQA
42.8Knowledge
AIME25
47.4Reasoning
HMMT25
31.0Reasoning
ZebraLogic
80.2Reasoning
LiveBench 20241125
63.0Reasoning
Every reported result25
LiveCodeBench v6 (25.02-25.05)
35.1Coding
MultiPL-E
76.8Coding
Aider-Polyglot
12.9Coding
IFEval
83.4Alignment
Arena-Hard v2
43.4Alignment
Creative Writing v3
83.5Alignment
WritingBench
83.4Alignment
BFCL-v3
61.9Agent
TAU1-Retail
48.7Agent
TAU1-Airline
32.0Agent
TAU2-Retail
40.4Agent
TAU2-Airline
24.0Agent
TAU2-Telecom
13.2Agent
MultiIF
69.0Multilingualism
MMLU-ProX
61.6Multilingualism
INCLUDE
60.1Multilingualism
PolyMATH
31.1Multilingualism
Across Qwen3 sizes25 shared results · same publisher and settings
Qwen3: results the publisher reports for each size under the same settings
Benchmark (publisher settings)4B Instruct 250730B A3B Instruct 2507
MMLU-Pro · Knowledge69.678.4
MMLU-Redux · Knowledge84.289.3
GPQA · Knowledge62.070.4
SuperGPQA · Knowledge42.853.4
AIME25 · Reasoning47.461.3
HMMT25 · Reasoning31.043.0
ZebraLogic · Reasoning80.290.0
LiveBench 20241125 · Reasoning63.069.0
LiveCodeBench v6 (25.02-25.05) · Coding35.143.2
MultiPL-E · Coding76.883.8
Aider-Polyglot · Coding12.935.6
IFEval · Alignment83.484.7
Arena-Hard v2 · Alignment43.469.0
Creative Writing v3 · Alignment83.586.0
WritingBench · Alignment83.485.5
BFCL-v3 · Agent61.965.1
TAU1-Retail · Agent48.759.1
TAU1-Airline · Agent32.040.0
TAU2-Retail · Agent40.457.0
TAU2-Airline · Agent24.038.0
TAU2-Telecom · Agent13.212.3
MultiIF · Multilingualism69.067.9
MMLU-ProX · Multilingualism61.672.0
INCLUDE · Multilingualism60.171.9
PolyMATH · Multilingualism31.143.1

Values as printed on the card, with the publisher's own settings (card section: Performance); column “Qwen3-4B-Instruct-2507”. Not comparable across publishers and not used in any ranking. Model card

Run it

Run it

File Q4_K_M · 2.5 GB · unsloth/Qwen3-4B-Instruct-2507-GGUF · What is Q4?

Measured 134.5 tok/s · MLX q4 · 1 machine · mlx-lm BENCHMARKS.md · all rows

ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_K_M
  1. Install Ollama
  2. Run the command above
  3. Ask: Explain what a context window is, in two sentences.

Runs on

Fast memory holds it 118

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 118

Within memory, outside the fast part 1

Within the machine's memory, outside its fast part: on a graphics card the layers that do not fit run on the CPU from PC RAM (the listed RAM, or 32 GB assumed); on a Mac, above the macOS default GPU share. Not a speed figure.

Qwen3 4B Instruct 2507 is a text model from Alibaba with 4B parameters. It was released on August 6, 2025 and reads up to 262,144 tokens of context. Its Q4 weights plus working room come to about 3 GB before the machine's reserve; the smallest reference machines whose fast memory holds that are Mac mini M2 · 8 GB unified (~5 GB with its reserve) and RTX 4060 · 8 GB VRAM (~5 GB with its reserve). We collected 29 downloadable GGUF and MLX files from 3 publisher sources; the most downloaded GGUF source is unsloth's. It has no result in LiveBench 2026-06-25, so no quality score is shown.

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Each card opens its hardware profile. Not a measured fit or speed.

On the reference machines

Qwen3 4B Instruct 2507 on the reference machines
Where Q4 sits
Mac mini M2 · 8 GB unifiedFast memory holds itQ6_KGGUF · 3.3 GB · needs ~8 GB8,192 tokens~5 GBFast memory holds itQ6_KGGUF · 3.3 GB · needs ~8 GB8,192 tokens
Mac mini M4 · 16 GB unifiedFast memory holds itQ8_0GGUF · 4.3 GB · needs ~11 GB32,768 tokens~7 GBFast memory holds itQ8_0GGUF · 4.3 GB · needs ~11 GB32,768 tokens
Mac mini M4 · 24 GB unifiedFast memory holds itQ8_0GGUF · 4.3 GB · needs ~13 GB65,536 tokens~9 GBFast memory holds itQ8_0GGUF · 4.3 GB · needs ~13 GB65,536 tokens
Mac mini M4 · 32 GB unifiedFast memory holds itQ8_0GGUF · 4.3 GB · needs ~15 GB65,536 tokens~11 GBFast memory holds itQ8_0GGUF · 4.3 GB · needs ~15 GB65,536 tokens
Mac mini M5 Pro · 64 GB unifiedFast memory holds itQ8_0GGUF · 4.3 GB · needs ~15 GB262,144 tokens~11 GBFast memory holds itQ8_0GGUF · 4.3 GB · needs ~15 GB262,144 tokens
Mac Studio M5 Max · 128 GB unifiedFast memory holds itQ8_0GGUF · 4.3 GB · needs ~15 GB262,144 tokens~11 GBFast memory holds itQ8_0GGUF · 4.3 GB · needs ~15 GB262,144 tokens
Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unifiedFast memory holds itQ8_0GGUF · 4.3 GB · needs ~15 GB262,144 tokens~11 GBFast memory holds itQ8_0GGUF · 4.3 GB · needs ~15 GB262,144 tokens
RTX 4060 · 8 GB VRAMFast memory holds itQ6_KGGUF · 3.3 GB · needs ~8 GB8,192 tokens~5 GBFast memory holds itQ6_KGGUF · 3.3 GB · needs ~8 GB8,192 tokens
RTX 3060 · 12 GB VRAMFast memory holds itQ8_0GGUF · 4.3 GB · needs ~9 GB32,768 tokens~5 GBFast memory holds itQ8_0GGUF · 4.3 GB · needs ~9 GB32,768 tokens
RTX 5080 · 16 GB VRAMFast memory holds itQ8_0GGUF · 4.3 GB · needs ~9 GB32,768 tokens~5 GBFast memory holds itQ8_0GGUF · 4.3 GB · needs ~9 GB32,768 tokens
RTX 4090 · 24 GB VRAMFast memory holds itQ8_0GGUF · 4.3 GB · needs ~9 GB65,536 tokens~5 GBFast memory holds itQ8_0GGUF · 4.3 GB · needs ~9 GB65,536 tokens
RTX 5090 · 32 GB VRAMFast memory holds itQ8_0GGUF · 4.3 GB · needs ~9 GB131,072 tokens~5 GBFast memory holds itQ8_0GGUF · 4.3 GB · needs ~9 GB131,072 tokens
DGX H100 · 8 × 80 GBFast memory holds itQ8_0GGUF · 4.3 GB · needs ~23 GB262,144 tokens~19 GBFast memory holds itQ8_0GGUF · 4.3 GB · needs ~23 GB262,144 tokens

The file column uses the site's quant ladder (Q8_0 to Q3_K_M, MLX 8 to 4-bit on a Mac): the largest collected file whose size × 1.2 plus the context cache and the machine's reserve fits the fast memory. Planning estimates, not measured runs.

Plan another quantization or context

Consider it for

Compare Qwen3 4B Instruct 2507 using its publisher card. No overall score appears in the LiveBench 2026-06-25 snapshot.

Check first

The Q4 weights plus working room come to about 3 GB from 4B stated parameters, before the machine's reserve (Runs on adds it per machine). It is not a measured minimum; context, batch size, runtime and quantization change actual memory use.

Versions to download

Files you can download for this checkpoint. The section opens on the most downloaded collected GGUF source, unsloth, at Q4_K_M. On a Mac it opens on the most downloaded MLX source. Sizes are the Hub's published bytes. What is Q4?

unsloth

unsloth/Qwen3-4B-Instruct-2507-GGUF · Qwen3-4B-Instruct-2507-Q4_K_M.gguf · 2.5 GB

Run this file

ollama run hf.co/unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_K_M
llama-server -hf unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_K_M
lms get https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-GGUF
  • mlx-lm: mlx-lm runs MLX repositories; pick the MLX version on a Mac

Quality scores on this page belong to the original checkpoint; these files are not scored or ranked. File sizes read 2026-10-23 · download counts read 2026-10-17 · commands: Hugging Face Hub docs: Use Ollama with any GGUF model · llama.cpp server README (-hf <user>/<model>[:quant]) · LM Studio docs: lms get with a Hugging Face URL · mlx-lm README (mlx_lm.generate --model)

Fine-tunes, adapters and other versions2,615 fine-tunes
Quantized versions
353
Fine-tunes
2,615
Adapters · merges
Not counted yet: the Hub's base-model lists are read by the weekly collector.

Browse them on the Hugging Face model tree · read 2026-10-23

Uncensored and abliterated versions22

Some community uploads remove the model's safety refusals. Quality may drop, the original publisher does not support them, claims about them are the uploader's, and the original license still applies. This site never recommends or ranks them.

22 derivative repositories have “uncensored” or “abliterated” in their name (read 2026-10-23).

Measured speed

Tokens per second by machine

Output tok/s · 1 machine · fastest 5 of 7 · every row in the table · What is a token?

Apple M4 Max · 64 GB · MLX q4, 134.52 · MLX q4134.5
Apple M4 Max · 64 GB · MLX q4 g32, 126.00 · MLX q4 g32126.0
Apple M4 Max · 64 GB · MLX q5, 116.39 · MLX q5116.4
Apple M4 Max · 64 GB · MLX q5 g32, 110.29 · MLX q5 g32110.3
Apple M4 Max · 64 GB · MLX q6, 104.68 · MLX q6104.7
Measured speed
Apple M4 Max · 64 GB (GPU cores not stated)134.52MLX q42048 / 128 · Single mlx_lm.benchmark processMLX (mlx-lm)mlx 0.29.2.dev20251008+85a8824a8 · mlx-lm 0.28.2 · macOS 26.1mlx-community/Qwen3-4B-Instruct-2507-4bit
Apple M4 Max · 64 GB (GPU cores not stated)126.00MLX q4 g322048 / 128 · Single mlx_lm.benchmark processMLX (mlx-lm)mlx 0.29.2.dev20251008+85a8824a8 · mlx-lm 0.28.2 · macOS 26.1mlx-community/Qwen3-4B-Instruct-2507-4bit-g32
Apple M4 Max · 64 GB (GPU cores not stated)116.39MLX q52048 / 128 · Single mlx_lm.benchmark processMLX (mlx-lm)mlx 0.29.2.dev20251008+85a8824a8 · mlx-lm 0.28.2 · macOS 26.1mlx-community/Qwen3-4B-Instruct-2507-5bit
Apple M4 Max · 64 GB (GPU cores not stated)110.29MLX q5 g322048 / 128 · Single mlx_lm.benchmark processMLX (mlx-lm)mlx 0.29.2.dev20251008+85a8824a8 · mlx-lm 0.28.2 · macOS 26.1mlx-community/Qwen3-4B-Instruct-2507-5bit-g32
Apple M4 Max · 64 GB (GPU cores not stated)104.68MLX q62048 / 128 · Single mlx_lm.benchmark processMLX (mlx-lm)mlx 0.29.2.dev20251008+85a8824a8 · mlx-lm 0.28.2 · macOS 26.1mlx-community/Qwen3-4B-Instruct-2507-6bit
Apple M4 Max · 64 GB (GPU cores not stated)86.907MLX q82048 / 128 · Single mlx_lm.benchmark processMLX (mlx-lm)mlx 0.29.2.dev20251008+85a8824a8 · mlx-lm 0.28.2 · macOS 26.1mlx-community/Qwen3-4B-Instruct-2507-8bit
Apple M4 Max · 64 GB (GPU cores not stated)52.47MLX bf162048 / 128 · Single mlx_lm.benchmark processMLX (mlx-lm)mlx 0.29.2.dev20251008+85a8824a8 · mlx-lm 0.28.2 · macOS 26.1Qwen/Qwen3-4B-Instruct-2507

Source: mlx-lm BENCHMARKS.md · maintainer result (checked 2026-10-25) · MLX (mlx-lm) · mlx 0.29.2.dev20251008+85a8824a8 · mlx-lm 0.28.2 · macOS 26.1 · not estimated

How to run

The memory needed above is the Q4 load before a machine's reserve. Formula: parameters × 0.625 bytes, plus 20% working allowance; each machine then adds its system reserve: 25% of unified or system memory, 2 to 8 GB, or 2 GB per GPU on dedicated cards. This is neither measured VRAM nor checkpoint download size.

Q4 planning estimate only. Check checkpoint format, runtime support, KV cache, context, batch size and offload before choosing hardware.

Evidence level: Generic estimate only; no execution reproduced by this site.

Publisher sampling defaults
temperature 0.7 · top_p 0.8 · top_k 20generation_config.json · read 2026-10-23source
Chat template markers
tool calls · no thinking markersmarkers found in the template, not a test of the feature · read 2026-10-23source
Before downloading
  1. Check the exact checkpoint and license linked here.
  2. Confirm a compatible runtime and precision or quantization for your platform.
  3. Allow for context, batch size and any extra media components beyond the weights.

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Checkpoint / version
Qwen/Qwen3-4B-Instruct-2507
Task and modality
language and reasoning · text
Count and basis
4B · manufacturer specificationQwen/Qwen3-4B-Instruct-2507 model card (Hugging Face) · read 2026-10-17source
Context
262,144 tokens published for this modelQwen/Qwen3-4B-Instruct-2507 model card (Hugging Face) · read 2026-10-17source
Architecture
DenseQwen/Qwen3-4B-Instruct-2507 config.json (Hugging Face) · read 2026-10-17source
Released
QwenLM/Qwen3 README (GitHub) · read 2026-10-09source
Runtime and precision
No local execution verified.
Commercial use
Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
Every stored field13 fields
Revision checked
cdbee75f17c01a7cc42f958dc650907174af0554
Architecture
Qwen3ForCausalLM
Library
transformers
Hub task tag
text-generation
Formats
safetensors
Access
Open download
Publisher kind
Official
Tensor evidence
floating-tensor-elements · 4.02B · BF16checked 2026-09-26
Repository created
2025-08-05creation is not the model's release
Repository updated
2025-09-17a commit is not a release date
Hub downloads (30 days) · likes
2,577,859 · 1,027this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Catalog reviewed: 2026-10-17. Benchmark release: 2026-06-25; snapshot collected: 2026-10-18.