Open Model Catalog

30 deep-dive pages for the highest-traffic open models. Each page has exact VRAM tables, GPU-fit recommendations, community benchmarks, and download commands.

Showing 35 of 35 models
NomicEmbeddinglocal-ok

Nomic Embed Text v1.5

Nomic Embed Text v1.5 is the leading open long-context embedding model — supports 8192 tokens (16x BGE-Large) and uses Matryoshka representation learning, so you can truncate the 768-dim output to 256 or 128 dims with minimal accuracy loss. Apache 2.0 licensed and trained on fully open data. Tiny 137 M footprint runs on CPU; on GPU it embeds 200k+ chunks/sec.

Params
0.137B
Q4 VRAM
0 GB
Released
Feb 24
View hardware requirements
BGEEmbeddinglocal-ok

BGE-Large EN v1.5

BGE-Large EN v1.5 from BAAI is the reference English embedding model for RAG pipelines — produces 1024-dim vectors, scores near the top of MTEB retrieval benchmarks. The tiny 335 M footprint runs on CPU comfortably or 100k+ embeddings/sec on a single RTX 4090. The 512-token context cap is the main limitation versus Nomic Embed v1.5.

Params
0.335B
Q4 VRAM
0 GB
Released
Sep 23
View hardware requirements
Llama 3.2Text LLMlocal-ok

Llama 3.2 1B

Llama 3.2 1B is the smallest official Llama, designed for on-device deployment — it runs comfortably on a Snapdragon X Elite NPU, an Apple Neural Engine, or even a Raspberry Pi 5. Quality is naturally limited; it's best for summarization, classification, and tool-routing tasks rather than long-form generation. Expect 30-50 tok/s on midrange phones.

Params
1B
Q4 VRAM
1 GB
Released
Sep 24
View hardware requirements
WhisperSpeechlocal-ok

Whisper Large v3

Whisper Large v3 is OpenAI's flagship open speech-to-text model — supports 99 languages with leading WER scores. The Apache 2.0 license and tiny ~3 GB FP16 footprint make it deployable everywhere from Raspberry Pi (via whisper.cpp Q4) to datacenter. On an RTX 4090 it transcribes at ~50x real-time. Known weakness: occasional hallucinations on silence or low-resource languages.

Params
1.55B
Q4 VRAM
1 GB
Released
Nov 23
View hardware requirements
WhisperSpeechlocal-ok

WhisperX

WhisperX wraps Whisper Large v3 with faster-whisper batched inference, wav2vec2 forced alignment for word-level timestamps, and pyannote diarization for speaker identification — achieving up to 70x real-time on an RTX 4090. It's the recommended pipeline for subtitle generation, podcast transcription, and meeting recording analysis. Trade-off: more dependencies and a slightly more complex install than vanilla whisper.cpp.

Params
1.55B
Q4 VRAM
1 GB
Released
Oct 23
View hardware requirements
Llama 3.2Text LLMlocal-ok

Llama 3.2 3B

Llama 3.2 3B punches well above its weight thanks to knowledge distillation from the 8B model. It's the sweet spot for AI PCs with NPUs (Intel Core Ultra, Snapdragon X, Ryzen AI) and runs at 50-100+ tok/s on midrange consumer GPUs. Tool-use and short-form summarization are particularly strong; it can struggle with long reasoning chains.

Params
3B
Q4 VRAM
2 GB
Released
Sep 24
View hardware requirements
Stable DiffusionImage Generationlocal-ok

SDXL 1.0

SDXL 1.0 is the de-facto open image-generation model — its 3.5 B parameter U-Net plus dual text encoders produces 1024×1024 images with strong composition. The ecosystem (ControlNet, LoRAs, IP-Adapter, refiner) is unmatched among open models. Runs on any 8 GB+ GPU; an RTX 4090 hits ~28 img/min at 30 steps. FLUX.1 dev has surpassed it on quality but the SDXL tooling lead remains significant.

Params
3.5B
Q4 VRAM
2 GB
Released
Jul 23
View hardware requirements
PhiText LLMlocal-ok

Phi-3.5 Mini 3.8B

Phi-3.5 Mini is Microsoft's curated-synthetic-data 3.8 B model — rivals 7-13 B models on reasoning despite the small size. Particularly notable for the 128K context window in such a small footprint. Runs at 100+ tok/s on midrange consumer GPUs at Q4_K_M (only ~2.3 GB VRAM). Weakness: limited world knowledge versus naturally-trained peers.

Params
3.8B
Q4 VRAM
2 GB
Released
Aug 24
View hardware requirements
PhiText LLMlocal-ok

Phi-4 Mini 3.8B

Phi-4 Mini is Microsoft's February 2025 successor to Phi-3.5 Mini — same 3.8 B footprint but with first-class function calling, a 128K context window, and a tokenizer overhaul that doubles non-English efficiency. It beats Phi-3.5 Mini on every reasoning benchmark and approaches Phi-4 14B on math while running at ~2.3 GB VRAM at Q4_K_M. MIT licensed. The realistic deployment target: AI PCs with NPUs, mini PCs, edge servers, and even a Raspberry Pi 5 via llama.cpp. For a Lagos solo dev on a 6 GB laptop GPU, this is the local agent model that actually fits.

Params
3.8B
Q4 VRAM
2 GB
Released
Feb 25
View hardware requirements
Qwen 2.5Text LLMlocal-ok

Qwen 2.5 7B

Qwen 2.5 7B is Alibaba's flagship small model — particularly strong on Chinese, math, and code benchmarks where it edges out Llama 3.1 8B. The Apache 2.0 license makes it the preferred 7B for commercial deployments. Runs at 60-100 tok/s on a single RTX 4060 8 GB at Q4_K_M.

Params
7B
Q4 VRAM
4 GB
Released
Sep 24
View hardware requirements
MistralText LLMlocal-ok

Mistral 7B

Mistral 7B v0.3 remains the reference small open model — first to popularize sliding-window attention and grouped-query attention. It's been surpassed on raw benchmarks by Llama 3.1 8B and Qwen 2.5 7B, but its Apache 2.0 license and massive ecosystem of fine-tunes keep it relevant. Excellent base for custom fine-tunes.

Params
7B
Q4 VRAM
4 GB
Released
Sep 23
View hardware requirements
Llama 3.1Text LLMlocal-ok

Llama 3.1 8B

Llama 3.1 8B is Meta's best-in-class small dense model — competitive with much larger 13B-class models on reasoning and instruction following. It's fast enough for single-GPU local chat on 8 GB cards at Q4 and ships with full 128K context support. The weakness is that it still trails 70B-class models on multi-step reasoning and tool use.

Params
8B
Q4 VRAM
5 GB
Released
Jul 24
View hardware requirements
GraniteText LLMlocal-ok

Granite 3.2 8B Instruct

Granite 3.2 8B Instruct is IBM's February 2025 reasoning model — same 8 B footprint as Llama 3.1 8B but trained on a fully audited corpus that IBM will indemnify enterprise customers against. It ships with a toggleable thinking mode for chain-of-thought reasoning and matches or beats Llama 3.1 8B on most leaderboards. The pitch is not raw quality, it is the legal and procurement story: Apache 2.0 weights, documented training data, and IBM's enterprise SLA on watsonx.ai for buyers who cannot deploy Meta or Alibaba weights. Runs at 60-100 tok/s on a single RTX 4060 8 GB at Q4_K_M. For a regulated bank in Istanbul or a public-sector buyer in Lagos, this is often the only 8B model that clears procurement.

Params
8B
Q4 VRAM
5 GB
Released
Feb 25
View hardware requirements
Llama 3.2Vision LLMlocal-ok

Llama 3.2 Vision 11B

Llama 3.2 Vision 11B is Meta's accessible open multimodal model — handles image-grounded QA, chart reading, and document understanding well. Fits in 16 GB VRAM at Q4_K_M. Competitive with GPT-4V on common tasks but lags on dense-text OCR and very detailed visual reasoning where the 90B variant pulls ahead.

Params
11B
Q4 VRAM
7 GB
Released
Sep 24
View hardware requirements
FLUXImage Generationlocal-ok

FLUX.1 [dev]

FLUX.1 [dev] from Black Forest Labs (ex-Stability researchers) is the highest-quality open image model — beats SDXL and approaches Midjourney v6 on photorealism and prompt following. The 12 B parameter footprint demands ~24 GB VRAM at FP16, ~7 GB at Q4 (NF4) using community quants. The non-commercial license is the main adoption blocker; FLUX.1 [schnell] is the Apache-licensed alternative.

Params
12B
Q4 VRAM
7 GB
Released
Aug 24
View hardware requirements
Qwen 2.5Text LLMlocal-ok

Qwen 2.5 14B

Qwen 2.5 14B sits in the 'serious assistant' sweet spot — clearly better than 7B on multi-step reasoning while still fitting comfortably in 16 GB VRAM at Q4_K_M. It's a good choice for a single RTX 4070 Ti Super or 4080 build. Trade-off vs 7B is roughly 2x slower tok/s.

Params
14B
Q4 VRAM
9 GB
Released
Sep 24
View hardware requirements
PhiText LLMlocal-ok

Phi-4 14B

Phi-4 14B is Microsoft's late-2024 release that pushes synthetic-data training to its limit — beats Llama 3.3 70B on MATH and GPQA Diamond despite being 5x smaller. The MIT license is permissive for commercial use. Fits in 16 GB VRAM at Q4_K_M with usable context. Weakness: only a 16K context window, and limited multilingual depth versus Qwen.

Params
14B
Q4 VRAM
9 GB
Released
Dec 24
View hardware requirements
DeepSeek CoderCode LLMlocal-ok

DeepSeek-Coder-V2 16B

DeepSeek-Coder-V2 16B (Lite) is a 16 B MoE with 2.4 B activated params, designed for fast code completion. It matches GPT-4 Turbo on HumanEval and supports 338 programming languages with a 128K context window. At Q4_K_M it runs at 60-100 tok/s on a single RTX 4090, making it the strongest local code assistant in this class. The bigger 236 B Coder-V2 variant exists for datacenter use.

Params
16B
Q4 VRAM
10 GB
Released
Jun 24
View hardware requirements
Llama 4Text LLM

Llama 4 Maverick 17B

Llama 4 Maverick is Meta's flagship multimodal MoE — 400 B total parameters across 128 experts with 17 B activated per token. Benchmarks place it near GPT-4o on reasoning and beating Llama 3.1 405B at far lower per-token cost. Realistically it requires a 4x or 8x H100 / B200 cluster (~900 GB at FP16, ~245 GB at Q4_K_M). Not a homelab model.

Params
17B
Q4 VRAM
242 GB
Released
Apr 25
View hardware requirements
DeepSeek R1Text LLMlocal-ok

DeepSeek-R1-Distill-Qwen-32B

This distillation transfers R1's chain-of-thought reasoning into a 32 B dense Qwen-2.5 backbone — and it beats GPT-4o-mini and Claude 3.5 Sonnet on AIME and MATH benchmarks. At Q4_K_M it fits in 24 GB (RTX 4090 / 5090 / 3090) with usable context, making it the most accessible top-tier reasoning model for local users. Drawback: every output is preceded by a long <think> trace, so latency-to-first-useful-token is high.

Params
32B
Q4 VRAM
19 GB
Released
Jan 25
View hardware requirements
Qwen 2.5Text LLMlocal-ok

Qwen 2.5 32B

Qwen 2.5 32B is the strongest model that reliably fits in a single 24 GB consumer GPU at Q4_K_M. It outperforms Llama 3.1 70B on Chinese benchmarks and is competitive on English reasoning. Combined with the Apache 2.0 license, it's the go-to model for prosumer workstation deployments.

Params
32B
Q4 VRAM
19 GB
Released
Sep 24
View hardware requirements
Qwen 2.5Code LLMlocal-ok

Qwen 2.5 Coder 32B

Qwen 2.5 Coder 32B is currently the best open-weight coding model — it tops HumanEval, MBPP, and LiveCodeBench while supporting 92 programming languages and a 128K context for whole-repo reasoning. Fits in 24 GB at Q4_K_M, making it deployable on a single RTX 4090 / 5090 / 3090. The natural replacement for DeepSeek-Coder-V2 when you want dense-model quality.

Params
32B
Q4 VRAM
19 GB
Released
Nov 24
View hardware requirements
Qwen 3Text LLMlocal-ok

Qwen 3 32B

Qwen 3 32B is the largest Qwen 3 that fits in a single 24 GB consumer GPU at Q4_K_M — and on reasoning benchmarks it closes most of the gap to the 72B sibling thanks to the hybrid thinking mode. For a Lagos or Istanbul builder running a single RTX 4090 or 5090, this is the strongest local model you can run without resorting to MoE offload. Apache 2.0, 128K context, full multilingual support. The thinking mode produces noticeably longer outputs than Qwen 2.5 32B, so expect tok/s to feel slower at identical hardware unless you disable it.

Params
32B
Q4 VRAM
19 GB
Released
Apr 25
View hardware requirements
MistralText LLMlocal-ok

Mixtral 8x7B

Mixtral 8x7B was the first widely successful open MoE — 47 B total weights but only 12.9 B activated per token. It needs all weights in VRAM (~26 GB at Q4_K_M), so practically a single 32 GB GPU (RTX 5090, A6000) or 2x 16 GB cards. The Apache 2.0 license and competitive Llama 2 70B-class quality made it a homelab favorite, though Llama 3.1 70B has largely superseded it.

Params
46.7B
Q4 VRAM
28 GB
Released
Dec 23
View hardware requirements
Llama 3.1Text LLMlocal-ok

Llama 3.1 70B

Llama 3.1 70B is the workhorse of self-hosted AI in 2024-2026 — competitive with GPT-4-class proprietary models on most benchmarks. At Q4_K_M it fits in a single RTX 4090 or 5090 (24-32 GB) with reduced context, or comfortably on dual 24 GB cards. The trade-off versus 8B is roughly 5-8x slower tok/s on identical hardware.

Params
70B
Q4 VRAM
42 GB
Released
Jul 24
View hardware requirements
Llama 3.3Text LLMlocal-ok

Llama 3.3 70B

Llama 3.3 70B is Meta's late-2024 refresh that distills 405B-style instruction quality into the 70B footprint — it beats Llama 3.1 70B on MATH, GPQA, and IFEval while keeping the same VRAM and tok/s envelope. It is the default 70B-class recommendation for new local deployments. Hardware requirements are identical to Llama 3.1 70B (24 GB at Q4 with reduced context).

Params
70B
Q4 VRAM
42 GB
Released
Dec 24
View hardware requirements
Qwen 2.5Text LLMlocal-ok

Qwen 2.5 72B

Qwen 2.5 72B is Alibaba's flagship dense model, neck-and-neck with Llama 3.1 70B and pulling ahead on Chinese, math, and coding. VRAM footprint mirrors Llama 70B (~158 GB FP16, ~44 GB Q4_K_M). Note the license is Qwen-specific, not Apache, which limits some commercial uses above 100M MAU.

Params
72B
Q4 VRAM
44 GB
Released
Sep 24
View hardware requirements
Qwen 3Text LLMlocal-ok

Qwen 3 72B

Qwen 3 72B is Alibaba's April 2025 flagship dense release and the first major open model to ship a hybrid thinking mode — one set of weights, two behaviors. Set enable_thinking=true for o1-style chain-of-thought on math and code, or false for fast direct answers. It tops Qwen 2.5 72B on AIME, LiveCodeBench, and BFCL while inheriting Qwen's strong multilingual coverage (119 languages). Apache 2.0 license, identical VRAM footprint to Qwen 2.5 72B. At Q4_K_M it fits across 2x RTX 4090 (48 GB) or 1x H100 80 GB. The reasoning mode roughly doubles output tokens, so plan KV-cache headroom accordingly. See [Q4_K_M quantization](/glossary/q4-k-m) for the math.

Params
72B
Q4 VRAM
44 GB
Released
Apr 25
View hardware requirements
Llama 4Text LLM

Llama 4 Scout 17B

Llama 4 Scout is Meta's first MoE Llama — 109 B total parameters, 17 B per-token compute, 16 experts. The headline feature is a 10M-token context window (per Meta's April 2025 announcement), enabling whole-codebase or whole-book reasoning. Hardware-wise it's awkward: you must hold all 109 B weights in VRAM (~240 GB at FP16, ~66 GB at Q4_K_M from the table below), but per-token compute is only 17 B — so a single H100 80 GB at Q4 is the practical entry point for inference, or 2x H100 for FP16. See our [Q4_K_M quantization](/glossary/q4-k-m) and [MoE architecture](/glossary/moe) glossary entries for the math, and the [/benchmarks](/benchmarks) page for measured tok/s.

Params
109B
Q4 VRAM
66 GB
Released
Apr 25
View hardware requirements
MistralText LLM

Mistral Large 2 123B

Mistral Large 2 is Mistral's flagship dense model — particularly strong on European languages (French, German, Spanish, Italian) and code (HumanEval ~92%). VRAM footprint is steep: ~270 GB FP16, ~75 GB Q4_K_M. Requires 2x H100, 4x A100 40 GB, or 4x RTX 6000 Ada. The Mistral Research License limits commercial deployment without a paid agreement.

Params
123B
Q4 VRAM
74 GB
Released
Jul 24
View hardware requirements
MistralText LLM

Mixtral 8x22B

Mixtral 8x22B is the bigger sibling — 141 B total, 39 B active, with stronger multilingual and reasoning performance. VRAM is brutal: ~310 GB FP16, ~85 GB Q4_K_M. Realistically a 4x RTX 6000 Ada (192 GB) or 2x H100 (160 GB at Q4) setup. Beaten on raw quality by Llama 3.1 70B at a smaller footprint, so adoption has been limited.

Params
141B
Q4 VRAM
85 GB
Released
Apr 24
View hardware requirements
Llama 3.1Text LLM

Llama 3.1 405B

Llama 3.1 405B is the largest open-weight Llama and arguably the highest-quality open base model ever released. At FP16 it requires ~890 GB of VRAM, meaning 8x H100 / B200 minimum; at Q4_K_M it still demands ~245 GB. It's not a homelab model — but quantized aggressively across 4x A100 80 GB it becomes usable for research workloads.

Params
405B
Q4 VRAM
245 GB
Released
Jul 24
View hardware requirements
DeepSeek R1Text LLM

DeepSeek-R1 671B

DeepSeek-R1 is the open MoE reasoning model that closed the gap with OpenAI o1 — and the first model to publish RL-from-verifiable-reward methodology. With 671 B total / 37 B active parameters, it requires datacenter hardware: ~1340 GB at FP16, ~370 GB at Q4_K_M. Practically, an 8x H100 or 8x B200 server is the floor; some users run Q4 across 8x RTX 6000 Ada (384 GB total) but throughput is constrained.

Params
671B
Q4 VRAM
406 GB
Released
Jan 25
View hardware requirements
DeepSeek V3Text LLM

DeepSeek V3 671B

DeepSeek V3 is the 671 B MoE base model (37 B active) that DeepSeek used as the starting point for R1. It beats Llama 3.1 405B on most benchmarks at a fraction of the compute, thanks to MLA attention and FP8 mixed-precision training. Inference VRAM mirrors R1 — ~370 GB at Q4_K_M, requiring multi-GPU datacenter hardware. Recommended over R1 when you want fast responses without the <think> overhead.

Params
671B
Q4 VRAM
406 GB
Released
Dec 24
View hardware requirements
DeepSeek V3Text LLM

DeepSeek V3-0324

DeepSeek V3-0324 is the March 24, 2025 refresh — same 685 B / 37 B-active MoE architecture as base V3, retrained with R1-style reasoning distillation and an MIT license (a meaningful upgrade from the original V3's bespoke DeepSeek license). On MATH-500, AIME, GPQA, and LiveCodeBench it lands between base V3 and R1 while still producing direct answers (no <think> trace). VRAM math is the same as base V3: ~1370 GB FP16, ~378 GB Q4_K_M — so 8x H100 or 8x B200 is the floor. For Lagos and Istanbul builders this is a cloud-API model, not a homelab one. See our [MoE architecture](/glossary/moe) glossary entry for why only 37 B of the 685 B is touched per token.

Params
685B
Q4 VRAM
414 GB
Released
Mar 25
View hardware requirements