Catalog snapshot updated 2026-11-16

AI Model Families for Local Inference

Browse open-weight model families you can run locally with Ollama. Each family page shows all variants, RAM requirements, device compatibility, and performance expectations.

models tracked
201
local rows
157
quant classes
10
registry-verified
126
Catalog coverage

Quality-gated, not inflated

ModelFit tracks 201 models across 41 families, with 157 local rows. Every Ollama command is registry-verified before it ships, and low-quality 2-bit quants stay out of the ranking even when they technically exist.

Default policy
Q4_K_M is the default recommendation tier; Q6/Q8 variants appear when they add real quality headroom.
Freshness
Catalog snapshot updated 2026-11-16; new tags enter through the registry-check pipeline, not from scraped guesses.
Honest coverage
A smaller verified catalog beats a bigger list padded with broken tags and unusable quants.
Table 1Local-runnable models

AI model families for local use

8 families
FamilyMakerModelsSizesNotes
QwenAlibaba Cloud400.5B-235BQwen is Alibaba Cloud's open-weight model family spanning 0.5B to 2.4T parameters. Qwen3.8 27B is the local flagship: a dense, Apache 2.0 vision-language model, while the Qwen3.8 2.4T A95B MoE tops the cloud line.Qwen3.8 27B local flagship (Apache 2.0, vision) · Cloud line tops out at the 2.4T A95B MoE
LlamaMeta121B-405BLlama is Meta's open-weight model family and the most popular choice for local AI. The Llama 4 line brings multimodal MoE models for big-memory machines, while the 1B-70B Llama 3.x sizes remain the practical laptop and desktop picks.Most popular open-weight model family · Strong general reasoning and instruction following
DeepSeekDeepSeek AI87B-671BDeepSeek now ships two distinct lines. The V4 generation is cloud-first: V4.1 Flash is an MIT-licensed multimodal image + text MoE, and V4 Flash 0731 and V4 Pro are API models. On consumer hardware DeepSeek means the R1 reasoning distills, from 7B up to the full 671B, all registry-verified in Ollama.V4.1 Flash: multimodal 552B MoE, API only · R1 distills 7B-70B run locally in Ollama
MistralMistral AI143.4B-123BMistral AI's models are known for efficiency and strong performance relative to their size. Mistral 7B was a breakthrough that proved small models could compete with much larger ones.Excellent performance-per-parameter ratio · Sliding window attention for efficiency
GemmaGoogle DeepMind191B-31BGemma is Google DeepMind's efficient open model family, tuned for strong quality at small sizes. The Gemma 4 line spans an on-device 4.5B model up to a dense 31B and a 26B MoE, all Apache 2.0.Gemma 4 E4B: 4.5B effective, runs on 8GB Macs · Gemma 4 26B-A4B MoE: 25.2B total, 3.8B active
PhiMicrosoft63.8B-14BPhi is Microsoft's small-but-mighty model family, built on the idea that careful training data beats raw parameter count. Phi-4 Mini packs strong reasoning into just 3.8B parameters, while Phi-4 14B competes with much larger models on quality. Both run locally with Ollama and pair naturally with low-RAM Apple Silicon Macs.Best quality-per-gigabyte at small sizes · Phi-4 Mini 3.8B loads in just 3.2GB (7GB min RAM)
LFM2Liquid AI28.3B-24BLFM2 is Liquid AI's efficiency-focused model family, built on a hybrid architecture rather than a standard dense transformer. Its flagship, LFM2 24B-A2B, is a sparse mixture-of-experts model that activates only 2B of its 24B parameters per token. That design makes it fast on consumer hardware and well suited to agent workflows, tool calling, and privacy-sensitive local setups.Hybrid MoE design: 24B total parameters, only 2B active per token · Loads in about 14GB, fits any 16GB Mac
SmolLMHugging Face10.36B-0.36BSmolLM is Hugging Face's ultra-tiny model family for the most constrained devices. SmolLM2 360M loads in about 0.5GB and runs on anything with 1GB of RAM, from old Macs and iPhones to embedded boards. It is the smallest model in our database and the fastest by speed score.Tiny 360M-parameter model from Hugging Face · Loads in about 0.5GB, needs just 1GB of RAM
Beyond consumer hardware

API-only & open-weights flagships

Frontier models you don't run on a laptop: hosted APIs, often with open weights. Each page says what it does and lists the local alternatives that actually fit your machine.

Browse every model

156 model pages

DeepSeek11

Gemma12

LFM22

Llama8

Mistral13

Other models77

Phi4

Qwen28

SmolLM1

Table 2Every tracked model

Full model catalog

Filter every tracked model by RAM, family, runtime and context budget. Load figures and fit rules come from the same dataset that powers the wizard.

201 of 201 models
FamilyQuantLocalollama
Qwen2.5 1.5B InstructQwen1.5BQ4_K_M4 GB~1.5 GBYesqwen2.5:1.5b-instruct-q4_K_M
Qwen2.5 3B InstructQwen3BQ4_K_M4 GB~2.5 GBYesqwen2.5:3b-instruct-q4_K_M
Qwen2.5 7B InstructQwen7BQ4_K_M8 GB~5.5 GBYesqwen2.5:7b-instruct-q4_K_M
Qwen2.5 14B InstructQwen14BQ4_K_M16 GB~11 GBYesqwen2.5:14b-instruct-q4_K_M
Llama 3.2 3B InstructLlama3BQ4_K_M4 GB~2.5 GBYesllama3.2:3b-instruct-q4_K_M
Llama 3.1 8B InstructLlama8BQ4_K_M12 GB~6.5 GBYesllama3.1:8b-instruct-q4_K_M
Llama 3.1 8B Instruct (Q8)Llama8BQ8_016 GB~8 GBYesllama3.1:8b-instruct-q8_0
Llama 3.1 8B Instruct (Q5)Llama8BQ5_K_M12 GB~8 GBYesllama3.1:8b-instruct-q5_K_M
Llama 3.1 70B InstructLlama70BQ4_K_M64 GB~42 GBYesllama3.1:70b-instruct-q4_K_M
Mistral 7B InstructMistral7BQ4_K_M8 GB~5.5 GBYesmistral:7b-instruct-v0.3-q4_K_M
Mistral 7B Instruct (Q5)Mistral7BQ5_K_M8 GB~4.8 GBYesmistral:7b-instruct-v0.3-q5_K_M
Mistral 7B Instruct (Q8)Mistral7BQ8_016 GB~7.2 GBYesmistral:7b-instruct-v0.3-q8_0
Mixtral 8x7B InstructMistral46.7BQ4_K_M48 GB~30 GBYesmixtral:8x7b
Mistral Nemo 12BMistral12BQ4_K_M16 GB~9.5 GBYesmistral-nemo:12b
Mistral Nemo 12B (Q8)Mistral12BQ8_024 GB~12.1 GBYesmistral-nemo:12b-instruct-2407-q8_0
Gemma 2 2B InstructGemma2BQ4_K_M4 GB~1.8 GBYesgemma2:2b-instruct-q4_K_M
Gemma 2 9B InstructGemma9BQ4_K_M12 GB~7 GBYesgemma2:9b-instruct-q4_K_M
Gemma 2 27B InstructGemma27BQ4_K_M32 GB~21 GBYesgemma2:27b-instruct-q4_K_M
Phi-3 Mini 3.8BPhi3.8BQ4_K_M6 GB~3.2 GBYesphi3:3.8b-mini-4k-instruct-q4_K_M
Phi-3 Medium 14BPhi14BQ4_K_M16 GB~11 GBYesphi3:14b-medium-4k-instruct-q4_K_M
Phi-4 14BPhi14BQ4_K_M24 GB~11.5 GBYesphi4:14b-q4_K_M
Phi-4 14B (Q8)Phi14BQ8_024 GB~14.5 GBYesphi4:14b-q8_0
Qwen2.5 Coder 7BQwen7BQ4_K_M8 GB~5.5 GBYesqwen2.5-coder:7b
Qwen2.5 Coder 14BQwen14BQ4_K_M16 GB~11 GBYesqwen2.5-coder:14b
Llama 3.2 1B InstructLlama1BQ4_K_M2 GB~1 GBYesllama3.2:1b-instruct-q4_K_M
Mistral Small 22BMistral22BQ4_K_M32 GB~17 GBYesmistral-small:22b
Kimi K2 InstructKimi1000BAPI0 GBn/aOpen, no fitn/a
Claude 3.5 SonnetClaudeUndisclosedAPI0 GBn/aCloudn/a
Claude 3.7 SonnetClaudeUndisclosedAPI0 GBn/aCloudn/a
Claude 3 OpusClaudeUndisclosedAPI0 GBn/aCloudn/a
Claude 4 OpusClaudeUndisclosedAPI0 GBn/aCloudn/a
Qwen2.5 0.5B InstructQwen0.5BQ4_K_M2 GB~0.8 GBYesqwen2.5:0.5b-instruct-q4_K_M
Gemma 3 1B InstructGemma1BQ4_K_M2 GB~1 GBYesgemma3:1b
Gemma 3 1B Instruct (Q8)Gemma1BQ8_04 GB~1 GBYesgemma3:1b-it-q8_0
Phi-4 Mini 3.8BPhi3.8BQ4_K_M6 GB~3.2 GBYesphi4-mini:3.8b
Phi-4 Mini 3.8B (Q8)Phi3.8BQ8_08 GB~3.8 GBYesphi4-mini:3.8b-q8_0
Microsoft Mage-VL-CoworkMage4BQ4_K_M8 GB~2.7 GBYesn/a
SmolLM2 360MSmolLM0.36BQ4_K_M1 GB~0.5 GBYessmollm2:360m
Llama 3.3 70B InstructLlama70BQ4_K_M64 GB~42 GBYesllama3.3:70b-instruct-q4_K_M
Llama 3.1 405B InstructLlama405BQ4_K_M320 GB~243 GBYesllama3.1:405b-instruct-q4_K_M
DeepSeek-R1 671BDeepSeek671BQ4_K_M512 GB~380 GBYesdeepseek-r1:671b-q4_K_M
Qwen3 8BQwen8BQ4_K_M12 GB~6.5 GBYesqwen3:8b-q4_K_M
Qwen3 8B (Q8)Qwen8BQ8_016 GB~8.1 GBYesqwen3:8b-q8_0
Qwen3 14BQwen14BQ4_K_M16 GB~11 GBYesqwen3:14b-q4_K_M
Qwen3 30BQwen30BQ4_K_M32 GB~22 GBYesqwen3:30b-a3b-q4_K_M
Qwen3 30B (Q8)Qwen30BQ8_048 GB~30.3 GBYesqwen3:30b-a3b-q8_0
Qwen3 32BQwen32BQ4_K_M32 GB~20.2 GBYesqwen3:32b-q4_K_M
Qwen3 32B (Q8)Qwen32BQ8_064 GB~35.1 GBYesqwen3:32b-q8_0
Qwen3 Coder 30B-A3BQwen30.5BQ4_K_M32 GB~18.6 GBYesqwen3-coder:30b-a3b-q4_K_M
Qwen3 Coder 30B-A3B (Q8)Qwen30.5BQ8_048 GB~32.5 GBYesqwen3-coder:30b-a3b-q8_0
Gemma 3 4B InstructGemma4BQ4_K_M6 GB~3.5 GBYesgemma3:4b
Gemma 3 4B Instruct (Q8)Gemma4BQ8_08 GB~3.9 GBYesgemma3:4b-it-q8_0
Gemma 3 12B InstructGemma12BQ4_K_M16 GB~9.5 GBYesgemma3:12b
Gemma 3 27B InstructGemma27BQ4_K_M32 GB~21 GBYesgemma3:27b
DeepSeek-R1 Distill Qwen 7BDeepSeek7BQ4_K_M8 GB~5.5 GBYesdeepseek-r1:7b
DeepSeek-R1 Distill Qwen 7B (Q8)DeepSeek7BQ8_016 GB~7.5 GBYesdeepseek-r1:7b-qwen-distill-q8_0
DeepSeek-R1 Distill Qwen 14BDeepSeek14BQ4_K_M16 GB~11 GBYesdeepseek-r1:14b
DeepSeek-R1 Distill Qwen 14B (Q8)DeepSeek14BQ8_024 GB~14.6 GBYesdeepseek-r1:14b-qwen-distill-q8_0
DeepSeek-R1 Distill Qwen 32BDeepSeek32BQ4_K_M32 GB~19.9 GBYesdeepseek-r1:32b-qwen-distill-q4_K_M
DeepSeek-R1 Distill Qwen 32B (Q8)DeepSeek32BQ8_064 GB~34.8 GBYesdeepseek-r1:32b-qwen-distill-q8_0
DeepSeek-R1 Distill Llama 70BDeepSeek70BQ4_K_M64 GB~42 GBYesdeepseek-r1:70b
GPT-4oOpenAIUndisclosedAPI0 GBn/aCloudn/a
GPT-4o miniOpenAIUndisclosedAPI0 GBn/aCloudn/a
Claude 4 SonnetClaudeUndisclosedAPI0 GBn/aCloudn/a
Gemini 2.5 ProGoogleUndisclosedAPI0 GBn/aCloudn/a
Gemini 2.5 FlashGoogleUndisclosedAPI0 GBn/aCloudn/a
DeepSeek-V3DeepSeek671BAPI0 GBn/aOpen, no fitn/a
GLM-5Zhipu744BAPI0 GBn/aOpen, no fitn/a
GLM-4 PlusZhipuUndisclosedAPI0 GBn/aCloudn/a
Qwen3 235B A22BQwen235BQ4_K_M192 GB~130 GBYesqwen3:235b-a22b-q4_K_M
Mistral Small 3.1Mistral24BQ4_K_M24 GB~15 GBYesmistral-small3.1:24b
Mistral Small 3.1 (Q8)Mistral24BQ8_036 GB~23.3 GBYesmistral-small3.1:24b-instruct-2503-q8_0
DeepSeek-V3-0324DeepSeek671BAPI0 GBn/aOpen, no fitn/a
DeepSeek-R1DeepSeek671BAPI0 GBn/aOpen, no fitn/a
Qwen3.5 0.8B InstructQwen0.8BQ4_K_M2 GB~0.8 GBYesqwen3.5:0.8b
Qwen3.5 2B InstructQwen2BQ4_K_M4 GB~1.8 GBYesqwen3.5:2b
Qwen3.5 4B InstructQwen4BQ4_K_M6 GB~3.5 GBYesqwen3.5:4b
Qwen3.5 4B Instruct (Q8)Qwen4BQ8_08 GB~4.3 GBYesqwen3.5:4b-q8_0
Qwen3.5 9B InstructQwen9BQ4_K_M12 GB~7 GBYesqwen3.5:9b
Qwen3.5 35B-A3B InstructQwen35BQ4_K_M32 GB~20 GBYesqwen3.5:35b-a3b
Qwen3.5 27B InstructQwen27BQ4_K_M24 GB~16 GBYesqwen3.5:27b
Qwen3.5 27B Instruct (Q8)Qwen27BQ8_048 GB~27.1 GBYesqwen3.5:27b-q8_0
Qwen3.5 122B-A10B InstructQwen122BQ4_K_M96 GB~72 GBYesqwen3.5:122b-a10b
LFM2 24B-A2B InstructLFM224BQ4_K_M24 GB~14 GBYeslfm2:24b-a2b
LFM2.5 8B-A1BLFM28.3BQ4_K_M8 GB~5.5 GBYeslfm2.5:8b-a1b-q4_K_M
Granite 4.1 3B InstructGranite3BQ4_K_M4 GB~2 GBYesgranite4.1:3b
Granite 4.1 8B InstructGranite8BQ4_K_M8 GB~5.5 GBYesgranite4.1:8b
Qwen3.6 27BQwen27BQ4_K_M32 GB~18 GBYesqwen3.6:27b
Qwen3.8 27BQwen27BQ4_K_M24 GB~16.5 GBYesqwen3.8:27b
Qwen3.8 27B (Q8)Qwen27BQ8_048 GB~27.1 GBYesqwen3.8:27b-q8_0
Qwen3.6 35B-A3BQwen35BQ4_K_M32 GB~22 GBYesqwen3.6:35b-a3b
Gemma 4 31BGemma31BQ4_K_M32 GB~20 GBYesgemma4:31b
Gemma 4 31B (Q8)Gemma31BQ8_048 GB~30.9 GBYesgemma4:31b-it-q8_0
Gemma 4 26B-A4BGemma26BQ4_K_M24 GB~16 GBYesgemma4:26b
Gemma 4 E4BGemma4.5BQ4_K_M6 GB~4 GBYesgemma4:e4b
Gemma 4 E4B (Q8)Gemma4.5BQ8_016 GB~7.5 GBYesgemma4:e4b-it-q8_0
Gemma 4 E2BGemma2.3BQ4_K_M4 GB~2.3 GBYesgemma4:e2b
Gemma 4 E2B (Q8)Gemma2.3BQ8_08 GB~4.6 GBYesgemma4:e2b-it-q8_0
Llama 4 ScoutLlama109BQ4_K_M96 GB~67 GBYesllama4:scout
Llama 4 MaverickLlama400BQ4_K_M320 GB~245 GBYesllama4:maverick
Mistral Medium 3.5Mistral128BAPI0 GBn/aOpen (llama.cpp)n/a
Mistral Large 4Mistral1049BAPI0 GBn/aOpen, no fitn/a
DeepSeek V4 Flash 0731DeepSeek284BAPI0 GBn/aOpen (llama.cpp)n/a
DeepSeek V4 ProDeepSeek1600BAPI0 GBn/aOpen, no fitn/a
DeepSeek V4.1 FlashDeepSeek763.21BAPI0 GBn/aOpen, no fitn/a
Kimi K2.6Kimi1000BAPI0 GBn/aOpen, no fitn/a
GLM-5.1Zhipu744BAPI0 GBn/aOpen, no fitn/a
Claude Opus 4.7ClaudeUndisclosedAPI0 GBn/aCloudn/a
Claude Opus 4.8ClaudeUndisclosedAPI0 GBn/aCloudn/a
GPT-5.5OpenAIUndisclosedAPI0 GBn/aCloudn/a
Gemini 3.1 ProGoogleUndisclosedAPI0 GBn/aCloudn/a
Grok 4.3xAIUndisclosedAPI0 GBn/aCloudn/a
Gemma 4 12BGemma12BQ4_K_M12 GB~8 GBYesgemma4:12b
Claude Fable 5ClaudeUndisclosedAPI0 GBn/aCloudn/a
GLM-5.2Zhipu753BAPI0 GBn/aOpen, no fitn/a
Kimi K2.7-CodeKimi1000BAPI0 GBn/aOpen, no fitn/a
MiniMax M3MiniMax428BAPI0 GBn/aOpen, no fitn/a
Qwen3.7-PlusQwenUndisclosedAPI0 GBn/aCloudn/a
NVIDIA Nemotron 3 UltraNemotron550BAPI0 GBn/aOpen, no fitn/a
Xiaomi MiMo-V2-FlashMiMo309BAPI0 GBn/aOpen (llama.cpp)n/a
NVIDIA Nemotron Cascade 2 30B-A3BNemotron30BQ6_K36 GB~24 GBYesnemotron-cascade-2:30b
Poolside Laguna XS.2Laguna33BQ4_K_M36 GB~23 GBYeslaguna-xs.2:q4_K_M
Cohere North Mini CodeNorth30BQ4_K_M32 GB~19 GBYesnorth-mini-code-1.0:q4_K_M
GPT-OSS 120BGPT-OSS117BMXFP496 GB~65.4 GBYesgpt-oss:120b
GPT-OSS 20BGPT-OSS21BMXFP424 GB~13.8 GBYesgpt-oss:20b
Qwen3-Next 80B-A3BQwen80BQ4_K_M72 GB~50.4 GBYesqwen3-next:80b
Qwen3.6 35B-A3B (Q8)Qwen35BQ8_064 GB~38.7 GBYesqwen3.6:35b-a3b-q8_0
Qwen3.5 35B-A3B Instruct (Q8)Qwen35BQ8_064 GB~38.7 GBYesqwen3.5:35b-a3b-q8_0
Qwen3.5 9B Instruct (Q8)Qwen9BQ8_016 GB~10.7 GBYesqwen3.5:9b-q8_0
Qwen3.6 27B (Q8)Qwen27BQ8_048 GB~30 GBYesqwen3.6:27b-q8_0
Gemma 4 12B (Q8)Gemma12BQ8_024 GB~12.8 GBYesgemma4:12b-it-q8_0
Gemma 4 26B-A4B (Q8)Gemma26BQ8_048 GB~28.1 GBYesgemma4:26b-a4b-it-q8_0
Qwen3-Next 80B-A3B (Q8)Qwen80BQ8_0128 GB~84.8 GBYesqwen3-next:80b-a3b-instruct-q8_0
Qwen3 14B (Q8)Qwen14BQ8_024 GB~15.9 GBYesqwen3:14b-q8_0
Llama 3.3 70B Instruct (Q8)Llama70BQ8_096 GB~75 GBYesllama3.3:70b-instruct-q8_0
Llama 3.3 70B Instruct (Q6)Llama70BQ6_K96 GB~57.9 GBYesllama3.3:70b-instruct-q6_K
Kimi K3Kimi2800BAPI0 GBn/aOpen, no fitn/a
Laguna XS 2.1Laguna33BQ4_K_M32 GB~20.3 GBYeslaguna-xs-2.1:q4_K_M
Laguna S 2.1Laguna118BQ4_K_M128 GB~96 GBYeslaguna-s-2.1:q4_K_M
Ornith 1.0 9BOrnith9BQ4_K_M8 GB~5.6 GBYesornith:9b
Ornith 1.0 35BOrnith35BQ4_K_M32 GB~21.2 GBYesornith:35b
Qwen3.8-Flash-NextQwen125BQ4_K_XL192 GB~111.3 GBYesn/a
Qwen3.8-Flash-Next (IQ4_XS)Qwen125BIQ4_XS128 GB~93.7 GBYesn/a
Qwen3.8-Flash-Next (Q3)Qwen125BQ3_K_XL128 GB~90 GBYesn/a
Qwen3.8 2.4T A95BQwen2400BAPI0 GBn/aOpen, no fitn/a
Granite 4.2 3BGranite3.7BQ4_K_M4 GB~2.1 GBYesgranite4.2:3b
Granite 4.2 8BGranite8.8BQ4_K_M8 GB~5 GBYesgranite4.2:8b
Granite 4.2 30BGranite29.3BQ4_K_M24 GB~16.5 GBYesgranite4.2:30b
Nemotron 3.5 Lightning 30B-A3BNemotron30BQ4_K_M36 GB~25.4 GBYesnemotron-3.5-lightning:30b
Nemotron 3.5 Lightning 30B-A3B (IQ4_XS)Nemotron30BIQ4_XS32 GB~18.9 GBYesn/a
Muse Glimmer 30BMuse29.8BQ4_K_M32 GB~16.9 GBYesmuse-glimmer:30b
MiniCPM-V 4.5 8BMiniCPM8.7BQ4_K_M12 GB~5.7 GBYesminicpm-v4.5:8b
GLM-5.3Zhipu753BAPI0 GBn/aOpen, no fitn/a
GLM-5.3 FlashZhipu321BAPI0 GBn/aOpen (llama.cpp)n/a
GLM-4.7-Flash 30B-A3BZhipu30BQ4_K_M32 GB~19 GBYesglm-4.7-flash
GLM-4-9B-ChatZhipu9.4BQ4_K_M12 GB~6.3 GBYesglm4:9b-chat-q4_K_M
GLM-4-9B-Chat (Q8)Zhipu9.4BQ8_016 GB~10 GBYesglm4:9b-chat-q8_0
Nemotron 3 Super 120B-A12BNemotron120BQ4_K_M128 GB~86.8 GBYesnemotron-3-super:120b
Nemotron 3 Super 120B-A12B (IQ4_XS)Nemotron120BIQ4_XS96 GB~64.5 GBYesn/a
Olmo 3.1 32B InstructOlmo32BQ4_K_M32 GB~19.5 GBYesolmo-3.1:32b
MiMo-V2.6-Distill-Qwen-9BMiMo9BQ4_K_M16 GB~5.8 GBYesn/a
Ling-3.0-flashLing124BQ4_K_M128 GB~77.8 GBYesn/a
Ling-3.0-flash (IQ4_XS)Ling124BIQ4_XS96 GB~68.7 GBYesn/a
Xiaomi MiMo-V2.6-FlashMiMo309BAPI0 GBn/aOpen (llama.cpp)n/a
Xiaomi MiMo-V2.6-ProMiMo1020BAPI0 GBn/aOpen, no fitn/a
Devstral Small 2 24BMistral24BQ4_K_M24 GB~15.2 GBYesdevstral-small-2:24b
Devstral 2 123BMistral123BQ4_K_M96 GB~74.9 GBYesdevstral-2:123b
Ministral 3 3BMistral3.4BQ4_K_M6 GB~3 GBYesministral-3:3b
Ministral 3 8BMistral8.4BQ4_K_M12 GB~6 GBYesministral-3:8b
Ministral 3 14BMistral13.5BQ4_K_M16 GB~9.1 GBYesministral-3:14b
Inkling SmallInkling276BAPI0 GBn/aOpen (llama.cpp)n/a
Flint 40B-A2.5BFlint39.8BNVFP436 GB~22.9 GBYesflint:40b
Mellum2.1 12B-A2.5B ThinkingMellum12.1BQ4_K_M16 GB~8.1 GBYesn/a
Kolibri 1Kolibri78.1BQ4_K_M96 GB~49.8 GBYesn/a
Kolibri 1 (IQ4_XS)Kolibri78.1BIQ4_XS64 GB~43.6 GBYesn/a
AREX-2 27BAREX27.4BQ4_K_M32 GB~17.2 GBYesn/a
Arete 27BArete27.4BQ4_K_M32 GB~17.2 GBYesn/a
TwIL-8BTwIL8.79BQ4_K_M8 GB~5.3 GBYesn/a
Nanbeige4.3 33BNanbeige33.1BQ4_K_M32 GB~20.8 GBYesn/a
Nanbeige4.3 33B (Q8)Nanbeige33.1BQ8_064 GB~35.2 GBYesn/a
Ripple 65B PreviewRipple64.8BQ4_K_M64 GB~38.8 GBYesripple-preview:65b-q4_K_M
Ripple 65B Preview (Q8)Ripple64.8BQ8_096 GB~68.8 GBYesn/a
Muse Spark OpenMuse816BAPI0 GBn/aOpen, no fitn/a
MiniMax M3.1 FlashMiniMax428BAPI0 GBn/aOpen, no fitn/a
MiniMax M3.1 FlashMiniMax428BQ4_K_XL512 GB~249.4 GBYesn/a
MiniMax M3.1 Flash (Q3_K_XL)MiniMax428BQ3_K_XL256 GB~194 GBYesn/a
Beam 1.0Beam501BAPI0 GBn/aOpen, no fitn/a
NVIDIA Nemotron 3.5 Bolt E4BNemotron4BQ4_K_M12 GB~7.9 GBYesnemotron-3.5-bolt:e4b
Granite Switch 4.1 8BGranite8.8BQ4_K_M12 GB~6.4 GBYesn/a
Granite Switch 4.1 30BGranite30BQ4_K_M32 GB~21 GBYesn/a
Jebadiah 9BJebadiah9BQ4_K_M12 GB~5.8 GBYesn/a
Jebadiah 9B (Q5)Jebadiah9BQ5_K_M12 GB~6.6 GBYesn/a
Jebadiah 9B (Q8)Jebadiah9BQ8_016 GB~9.8 GBYesn/a
Jebadiah 27BJebadiah27BQ4_K_M32 GB~16.8 GBYesn/a
Jebadiah 27B (Q5)Jebadiah27BQ5_K_M32 GB~19.5 GBYesn/a
Jebadiah 27B (Q8)Jebadiah27BQ8_048 GB~29 GBYesn/a
LFM3 1.7BLFM31.73BQ4_K_M4 GB~1.1 GBYeslfm3:1.7b
Ling-3.1-flash-1019Ling560BQ4_K_M512 GB~358 GBYesn/a
Tencent Hy4 PreviewHy770BIQ4_XS512 GB~417 GBYesn/a
Ornith 1.5 122BOrnith125.09BQ4_K_M128 GB~75.8 GBYesornith-1.5:122b
Sage-A1.5Sage35.95BQ4_K_M32 GB~21.7 GBYesn/a

How much RAM do you need?

Full breakdown on the stats page.

Explore by hardware