Llama 3.2 1B Instruct
Meta · meta-llama/Llama-3.2-1B-Instruct
Q4 file 0.8 GB (Q4_K_M) · runs well from 4 GB · Weights license: Publisher terms: Llama 3.2
Quality
- LMArena · text · rating
- 1,111 ± 8Confidence interval 1,103–1,119 · 8,045 votes · rank 400 of the releaseLMArena 2026-10-22 · CC BY 4.0
No result in LiveBench 2026-06-25 Not in LiveBench 2026-06-25
Reported by the publisher
- MMLU
- 49.3Llama 3.2 1B bf16 · Instruction Tuned Models · General
- Open-rewrite eval
- 41.6Llama 3.2 1B bf16 · Instruction Tuned Models · Re-writing
- TLDR9+ (test)
- 16.8Llama 3.2 1B bf16 · Instruction Tuned Models · Summarization
- IFEval
- 59.5Llama 3.2 1B bf16 · Instruction Tuned Models · Instruction following
- GSM8K (CoT)
- 44.4Llama 3.2 1B bf16 · Instruction Tuned Models · Math
- MATH (CoT)
- 30.6Llama 3.2 1B bf16 · Instruction Tuned Models · Math
- ARC-C
- 59.4Llama 3.2 1B bf16 · Instruction Tuned Models · Reasoning
- GPQA
- 27.2Llama 3.2 1B bf16 · Instruction Tuned Models · Reasoning
Every reported result
- Hellaswag
- 41.2Llama 3.2 1B bf16 · Instruction Tuned Models · Reasoning
- BFCL V2
- 25.7Llama 3.2 1B bf16 · Instruction Tuned Models · Tool Use
- Nexus
- 13.5Llama 3.2 1B bf16 · Instruction Tuned Models · Tool Use
- InfiniteBench/En.QA
- 20.3Llama 3.2 1B bf16 · Instruction Tuned Models · Long Context
- InfiniteBench/En.MC
- 38.0Llama 3.2 1B bf16 · Instruction Tuned Models · Long Context
- NIH/Multi-needle
- 75.0Llama 3.2 1B bf16 · Instruction Tuned Models · Long Context
- MGSM (CoT)
- 24.5Llama 3.2 1B bf16 · Instruction Tuned Models · Multilingual
- MMLU · Portuguese (5-shot, macro_avg/acc)
- 39.8Llama 3.2 1B · Multilingual Benchmarks · General · 5-shot
- MMLU · Spanish (5-shot, macro_avg/acc)
- 41.5Llama 3.2 1B · Multilingual Benchmarks · General · 5-shot
- MMLU · Italian (5-shot, macro_avg/acc)
- 39.8Llama 3.2 1B · Multilingual Benchmarks · General · 5-shot
- MMLU · German (5-shot, macro_avg/acc)
- 39.2Llama 3.2 1B · Multilingual Benchmarks · General · 5-shot
- MMLU · French (5-shot, macro_avg/acc)
- 40.5Llama 3.2 1B · Multilingual Benchmarks · General · 5-shot
- MMLU · Hindi (5-shot, macro_avg/acc)
- 33.5Llama 3.2 1B · Multilingual Benchmarks · General · 5-shot
- MMLU · Thai (5-shot, macro_avg/acc)
- 34.7Llama 3.2 1B · Multilingual Benchmarks · General · 5-shot
Across Llama 3.2 sizes
| Benchmark (publisher settings) | 1B Instruct | 3B Instruct |
|---|---|---|
| MMLU | 49.3 | 63.4 |
| Open-rewrite eval | 41.6 | 40.1 |
| TLDR9+ (test) | 16.8 | 19.0 |
| IFEval | 59.5 | 77.4 |
| GSM8K (CoT) | 44.4 | 77.7 |
| MATH (CoT) | 30.6 | 48.0 |
| ARC-C | 59.4 | 78.6 |
| GPQA | 27.2 | 32.8 |
| Hellaswag | 41.2 | 69.8 |
| BFCL V2 | 25.7 | 67.0 |
| Nexus | 13.5 | 34.3 |
| InfiniteBench/En.QA | 20.3 | 19.8 |
| InfiniteBench/En.MC | 38.0 | 63.3 |
| NIH/Multi-needle | 75.0 | 84.7 |
| MGSM (CoT) | 24.5 | 58.2 |
| MMLU · Portuguese (5-shot, macro_avg/acc) | 39.8 | 54.5 |
| MMLU · Spanish (5-shot, macro_avg/acc) | 41.5 | 55.1 |
| MMLU · Italian (5-shot, macro_avg/acc) | 39.8 | 53.8 |
| MMLU · German (5-shot, macro_avg/acc) | 39.2 | 53.3 |
| MMLU · French (5-shot, macro_avg/acc) | 40.5 | 54.6 |
| MMLU · Hindi (5-shot, macro_avg/acc) | 33.5 | 43.3 |
| MMLU · Thai (5-shot, macro_avg/acc) | 34.7 | 44.5 |
Values as printed on the card, with the publisher's own settings (card section: Benchmarks - English Text › Instruction Tuned Models; Benchmarks - English Text › Multilingual Benchmarks). Not comparable across publishers and not used in any ranking. Model card
Run it
Run it
File Q4_K_M · 0.8 GB · bartowski/Llama-3.2-1B-Instruct-GGUF · What is Q4?
ollama run hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_M- Install Ollama
- Run the command above
- Ask:
Explain what a context window is, in two sentences.
Runs on
Fast memory holds it 119
The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.
Show all 119
Llama 3.2 1B Instruct is a text model from Meta with 1.2B parameters. It was released on September 25, 2024 and reads up to 128,000 tokens of context. Its Q4 weights plus working room come to about 1 GB before the machine's reserve; the smallest reference machines whose fast memory holds that are Mac mini M2 · 8 GB unified (~3 GB with its reserve) and RTX 4060 · 8 GB VRAM (~3 GB with its reserve). We collected 17 downloadable GGUF and MLX files from 2 publisher sources; the most downloaded GGUF source is bartowski's. It has no result in LiveBench 2026-06-25. Its LMArena text rating is 1,111 ± 8 (release 2026-10-22), a separate human-preference scale.
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
| Where Q4 sits | ||||
|---|---|---|---|---|
| Mac mini M2 · 8 GB unifiedFast memory holds itQ8_0131,072 tokens | ~3 GB | Fast memory holds it | Q8_0 | 131,072 tokens |
| Mac mini M4 · 16 GB unifiedFast memory holds itQ8_0131,072 tokens | ~5 GB | Fast memory holds it | Q8_0 | 131,072 tokens |
| Mac mini M4 · 24 GB unifiedFast memory holds itQ8_0131,072 tokens | ~7 GB | Fast memory holds it | Q8_0 | 131,072 tokens |
| Mac mini M4 · 32 GB unifiedFast memory holds itQ8_0131,072 tokens | ~9 GB | Fast memory holds it | Q8_0 | 131,072 tokens |
| Mac mini M5 Pro · 64 GB unifiedFast memory holds itQ8_0131,072 tokens | ~9 GB | Fast memory holds it | Q8_0 | 131,072 tokens |
| Mac Studio M5 Max · 128 GB unifiedFast memory holds itQ8_0131,072 tokens | ~9 GB | Fast memory holds it | Q8_0 | 131,072 tokens |
| Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unifiedFast memory holds itQ8_0131,072 tokens | ~9 GB | Fast memory holds it | Q8_0 | 131,072 tokens |
| RTX 4060 · 8 GB VRAMFast memory holds itQ8_0131,072 tokens | ~3 GB | Fast memory holds it | Q8_0 | 131,072 tokens |
| RTX 3060 · 12 GB VRAMFast memory holds itQ8_0131,072 tokens | ~3 GB | Fast memory holds it | Q8_0 | 131,072 tokens |
| RTX 5080 · 16 GB VRAMFast memory holds itQ8_0131,072 tokens | ~3 GB | Fast memory holds it | Q8_0 | 131,072 tokens |
| RTX 4090 · 24 GB VRAMFast memory holds itQ8_0131,072 tokens | ~3 GB | Fast memory holds it | Q8_0 | 131,072 tokens |
| RTX 5090 · 32 GB VRAMFast memory holds itQ8_0131,072 tokens | ~3 GB | Fast memory holds it | Q8_0 | 131,072 tokens |
| DGX H100 · 8 × 80 GBFast memory holds itQ8_0131,072 tokens | ~17 GB | Fast memory holds it | Q8_0 | 131,072 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.
Compare Llama 3.2 1B Instruct using its publisher card. No overall score appears in the LiveBench 2026-06-25 snapshot.
The Q4 weights plus working room come to about 1 GB from 1.23B 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, bartowski, 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?
bartowski
bartowski/Llama-3.2-1B-Instruct-GGUF · Llama-3.2-1B-Instruct-Q4_K_M.gguf · 0.8 GB
Run this file
ollama run hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_Mllama-server -hf bartowski/Llama-3.2-1B-Instruct-GGUF:Q4_K_Mlms get https://huggingface.co/bartowski/Llama-3.2-1B-Instruct-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 versions
- Quantized versions
- 438
- Fine-tunes
- 1,843
- Adapters · merges
- 691 · 15
Browse them on the Hugging Face model tree · read 2026-10-23
Uncensored and abliterated versions
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.
8 derivative repositories have “uncensored” or “abliterated” in their name (read 2026-10-23).
Measured speed
No published measurement for this checkpoint
Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never 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 0.6 · top_p 0.9generation_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
- Check the exact checkpoint and license linked here.
- Confirm a compatible runtime and precision or quantization for your platform.
- 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
- meta-llama/Llama-3.2-1B-Instruct
- Task and modality
- language and reasoning · text
- Count and basis
- 1.23B · manufacturer specificationmeta-llama/llama-models Llama 3.2 MODEL_CARD.md (GitHub, publisher's own card; the Hub repo is gated) · read 2026-10-17source
- Context
- 128,000 tokens published for this modelmeta-llama/llama-models Llama 3.2 MODEL_CARD.md (GitHub, publisher's own card; the Hub repo is gated) · read 2026-10-17source
- Architecture
- Densemeta-llama/llama-models Llama 3.2 MODEL_CARD.md (GitHub, publisher's own card; the Hub repo is gated) · read 2026-10-17source
- Released
- Introducing Llama 3.2 (Meta AI blog), September 25, 2024: 1B and 3B models available for download · read 2026-10-10source
- Runtime and precision
- No local execution verified.
- Languages
- en, de, fr, it, pt, hi, es, thModel card metadata · read 2026-10-25source
- Commercial use
- Allowed with conditions Over 700M monthly users needs a Meta license; show "Built with Llama"; multimodal versions are not licensed to people or companies based in the EU (Acceptable Use Policy) · Llama 3.2 Community License (meta-llama/llama-models) · read 2026-10-18license text
Every stored field
- Revision checked
- 9213176726f574b556790deb65791e0c5aa438b6
- Architecture
- LlamaForCausalLM
- Library
- transformers
- Hub task tag
- text-generation
- Formats
- safetensors, pt
- Access
- Gated (manual)
- Publisher kind
- Official
- Tensor evidence
- floating-tensor-elements · 1.24B · BF16checked 2026-09-26
- Repository created
- 2024-09-18creation is not the model's release
- Repository updated
- 2024-10-24a commit is not a release date
- Hub downloads (30 days) · likes
- 3,488,705 · 1,891this 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.
- Publisher checkpoint and model card
- Weight license and use terms
- Quality benchmark source · LiveBench 2026-06-25 overall
Catalog reviewed: 2026-10-17. Benchmark release: 2026-06-25; snapshot collected: 2026-09-26.






























































