
Llama 3.2 3B Instruct
Model ranking
- Arena Score
- 1109.5658958184
- Arena reference rank
- 371
- Evaluation configuration
- Llama 3.2 3B Instruct
- Source published
- 2026-11-19
- Votes
- 7936
- Confidence lower
- 1102.0157491851
- Confidence upper
- 1117.1160424517
- Last successful check
- 2026-11-22T14:00:05.877Z
- Last value/rank change
- 2026-11-22T09:30:20.053Z
- Methodology
- Human preference — Text / overall; checked every six hours.
Source: Arena / LMArena ↗ · CC BY 4.0. Selection and catalog matching by XPU LIVE.
| Provider | Price | Provider model ID | Status | Context / max output | Source |
|---|---|---|---|---|---|
Cloudflare Workers AIllama-3.2-3b-instruct | Input$0.0509 Output$0.335 USD / 1M tokensUpdated 2026-10-20 | @cf/meta/llama-3.2-3b-instruct | Catalog-listedConditionsPublic catalog listing; account eligibility and capacity can vary. Verified component tariffs are supplied by the existing pricing engine. | Context tokens 80000 | Official source ↗2026-10-20 |
Llama 3.2 3B Instruct is Meta’s larger lightweight text model from the 3.2 release. It has its own weights and should not be merged with the 1B edition.
Llama 3.2 3B Instruct: suitable applications
Evaluate summarization, multilingual assistance and compact text applications with a predictable response format.
Capabilities and technical details
The model provides instruction tuning within the open-weight Llama ecosystem. A named size supports controlled comparisons with the smaller 1B variant.
Llama 3.2 3B Instruct accepts text and returns text. The recorded input reference is 80,000 tokens, with any lower Cloudflare cap recorded separately. The recorded terms are Llama 3.2 Community License; the linked source explains their scope.
Llama 3.2 3B Instruct limitations and selection
It does not inherit the image-input interface of the separate 11B Vision model. Provider caps and the Llama use conditions still apply.
Compare the 1B and 3B checkpoints on the same instruction-following tests, and include unsupported-language and out-of-domain requests in the failure analysis.
Llama 3.2 3B Instruct API pricing
Llama 3.2 3B Instruct pricing is tied to the selected endpoint and its documented token components. Compare input, output and cached-input charges only where those components are actually quoted; an absent component is not an invented free rate.
Review the Cloudflare Llama 3.2 3B Instruct endpoint reference and the Meta model documentation. Compare the linked Cloudflare Workers AI provider profile with the xpu live model directory when selecting a deployment.
Specifications
- Catalog model ID
- meta/llama-3.2-3b-instruct
- Developer model ID / revision
- Not verified in cited sources
- Input modalities
- textCloudflare Workers AI endpoint; route-specific capabilities ↗
- Output modalities
- textCloudflare Workers AI endpoint; route-specific capabilities ↗
- Context / input token limit
- 80,000Cloudflare Workers AI input cap ↗
- Maximum output tokens
- Not verified in cited sources
- Tool calling
- Not verified in cited sources
- Structured output
- Not verified in cited sources
- API parameters (source-specific)
- Not verified in cited sources
- Weight access
- Open weightsDeveloper model card / documentation ↗
- Weight license / access terms
- Llama 3.2 Community LicenseDeveloper weight license / hosted access terms ↗
- Total parameters (billions)
- 3Developer model card / documentation ↗
- Active parameters (billions)
- Not verified in cited sources
- Parameter-count details
- Developer-declared nominal model size; serialized tensor counts can differ. Active parameters, when supplied, are separate from total parameters.Developer model card ↗
- Download size (GB)
- Depends on checkpoint and precision; no verified file size
- Release date
- Not verified in cited sources
- Notes
- Cloudflare deployment limits and transport options are recorded on its offering. Weight license is separate from hosted-service conditions. Context shown here is the explicitly documented Cloudflare input cap; a separate publisher maximum is not verified. Parameter sizes are developer-declared nominal labels; serialized tensor counts may differ.
Catalog entries link to their specification and availability sources. This is a curated selection, not every model each provider offers. Best prices are the lowest collected USD tariffs, not a total-cost estimate. Token offers are selected by input price, with output from the same tariff; workload mix may change the cheapest provider. Listed variants may require batch processing, off-peak hours, or specific media settings. Price coverage varies by provider; collected tariffs include their source and observation time. Arena user-preference scores are checked automatically every six hours against the latest published Text / overall dataset. Source: Arena / LMArena; CC BY 4.0. Selection and catalog matching by XPU LIVE. They apply to the shown evaluation configuration; listed prices may use different settings. Models without verified scores are not assumed to be weaker.
