Run and distribute models
Ollama supplies model tags, downloads, a runtime and an API. Its library tells you what is available and how to launch it.
Confidence should be
visible, not implied.
LocalLens is a decision layer—not a model host, benchmark laboratory or replacement for Ollama and Hugging Face. This page separates sourced facts from LocalLens estimates and real machine tests.
43 curated profilesReviewed 20 August 20260 claimed LocalLens lab tests
Host and share AI artifacts
Hugging Face hosts model checkpoints, datasets, demos, model cards and community repositories across many frameworks.
Choose a realistic first test
LocalLens combines a curated artifact with hardware, task and context constraints, then explains fit, uncertainty and evidence.
CLAIM POLICY
What we may—and may not—say.
Parameter count, published context, input types, licence, artifact size and command are checked against the linked publisher or runtime page.
A linked independent test shows that a related artifact ran on named hardware. It does not prove identical speed elsewhere.
RAM and VRAM floors are conservative planning calculations. They are not publisher guarantees or measured performance.
This label is used only after DeviceTerra runs the exact artifact, quantization, context and runtime on documented hardware. No current profile carries this claim.
ENGINE EVIDENCE
Four levels prevent false compatibility.
LocalLens now checks the engine path before workflow preferences can influence the ranking.
The selected tag or file is directly present in the engine’s official catalogue. Every current LocalLens Ollama profile meets this level.
The engine’s current official documentation lists the architecture. A separate compatible checkpoint, GGUF or MLX artifact is still required.
The engine accepts a relevant format, but LocalLens has not confirmed this exact architecture and feature path. It cannot outrank stronger evidence without a warning.
The reviewed official documentation does not establish the model-to-engine path. LocalLens excludes it from recommendations instead of guessing.
MODEL-BY-MODEL STATUS
Every current recommendation profile
“Official checked” confirms source fields. “Community linked” adds a reproducible third-party configuration. Neither means DeviceTerra personally benchmarked it.
ProfileArtifactEvidenceLocalLens testSource
Qwen 3.6 27B Q4Alibaba Cloud · Dense
~17 GB · Q4-class Official checkedCommunity linkedNot lab-tested
Qwen 3.6 35B-A3B Q4Alibaba Cloud · MoE · 3B active
~24 GB · Q4-class Official checkedCommunity linkedNot lab-tested
Qwen 3 30B-A3BAlibaba Cloud · MoE · 3B active
~19 GB · Q4-class Official checkedNot lab-testedQwen 3 235B-A22BAlibaba Cloud · MoE · 22B active
~142 GB · Q4-class Official checkedNot lab-testedGemma 4 E2B QATGoogle · Dense
~4.3 GB · Q4-class Official checkedCommunity linkedNot lab-tested
Gemma 4 E4B QATGoogle · Dense
~6.1 GB · Q4-class Official checkedCommunity linkedNot lab-tested
Gemma 4 12B QATGoogle · Dense
~7.2 GB · Q4-class Official checkedCommunity linkedNot lab-tested
Gemma 4 26B-A4BGoogle · MoE · 4B active
~18 GB · Q4-class Official checkedCommunity linkedNot lab-tested
Gemma 4 31BGoogle · Dense
~20 GB · Q4-class Official checkedCommunity linkedNot lab-tested
GPT-OSS 120BOpenAI · MoE · 5.1B active
~65 GB · Native MXFP4 Official checkedNot lab-testedNemotron 3 Nano 4BNVIDIA · Dense
~2.8 GB · Q4-class Official checkedCommunity linkedNot lab-tested
Nemotron 3 Nano 30B-A3BNVIDIA · MoE · 3B active
~24 GB · Q4-class Official checkedCommunity linkedNot lab-tested
DeepSeek R1 1.5BDeepSeek · Dense
~1.1 GB · Q4-class Official checkedCommunity linkedNot lab-tested
DeepSeek R1 7BDeepSeek · Dense
~4.7 GB · Q4-class Official checkedCommunity linkedNot lab-tested
DeepSeek R1 8BDeepSeek · Dense
~5.2 GB · Q4-class Official checkedCommunity linkedNot lab-tested
DeepSeek R1 14BDeepSeek · Dense
~9 GB · Q4-class Official checkedCommunity linkedNot lab-tested
DeepSeek R1 32BDeepSeek · Dense
~20 GB · Q4-class Official checkedCommunity linkedNot lab-tested
DeepSeek R1 70BDeepSeek · Dense
~43 GB · Q4-class Official checkedCommunity linkedNot lab-tested
DeepSeek R1 671B MoEDeepSeek · MoE · 37B active
~404 GB · Q4-class Official checkedCommunity linkedNot lab-tested
Llama 4 Maverick 400BMeta · MoE · 17B active
~245 GB · Q4-class Official checkedNot lab-testedEmbeddingGemma 300MGoogle · Dense
~0.3 GB · Q8 Official checkedCommunity linkedNot lab-tested
The LocalLens accuracy contract
- Never convert another person’s tokens-per-second result into a promise for your computer.
- Never call a RAM estimate an official requirement.
- Never treat parameter count or one leaderboard score as proof that a model is best for every task.
- Always identify the artifact, quantization, context and runtime behind a recommendation.
- Remove or downgrade a profile when its evidence cannot be reproduced or its source changes.