All LLM Models
Browse 1242 LLM models with VRAM requirements, quantization options, and hardware compatibility.
Understanding LLM VRAM Requirements
How much VRAM you need depends on the model size and quantization level. Quantization reduces the precision of model weights, trading small quality losses for significantly lower VRAM usage. For example, a 7B parameter model needs ~14 GB at FP16 but only ~4 GB at Q4_K_M quantization.
Model List
FastVLM 7B
Apple · 7.8B · runs from 15.9 GB
1.6K
269FastVLM 7B is a 7.8B-parameter open language model from Apple. It supports a context window of up to 32,768 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Evo2 1B Base
Aquiles-ai · 1.1B · runs from 2.4 GB
Evo2 1B Base is a 1.1B-parameter open language model from Aquiles-ai. It supports a context window of up to 8,192 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Falcon H1 Tiny 90M Instruct
TII UAE · 91M · runs from 0.4 GB
Falcon H1 Tiny 90M Instruct is a 91M-parameter open language model from TII UAE in the Falcon family. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Steerling 8B
guidelabs · 8.4B · runs from 18.5 GB
Steerling 8B is a 8.4B-parameter open language model from guidelabs. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
LFM2.5 230M ONNX
Liquid AI · 230M · runs from 0.5 GB
LFM2.5 230M ONNX is a 230M-parameter open language model from Liquid AI in the LFM2.5 family. It supports a context window of up to 128,000 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
SupraElegans 500k
SupraLabs · 612391 · runs from 0.0 GB
SupraElegans 500k is a 612391-parameter open language model from SupraLabs. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Quasar 10B
silx-ai · 8.6B · runs from 17.8 GB
Quasar 10B is a 8.6B-parameter open language model from silx-ai. It supports a context window of up to 2,097,152 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Instinct Python Coder Gemma4 12B Qwen3.8 27B
projectj · 12B · runs from 5.6 GB
Instinct Python Coder Gemma4 12B Qwen3.8 27B is a 12B-parameter open language model from projectj in the Qwen 3.8 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qwen3 8B Abliterated
huihui-ai · 8.2B · runs from 3.8 GB
Qwen3 8B Abliterated is a 8.2B-parameter open language model from huihui-ai in the Qwen 3 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Llama Poro 2 8B Instruct
LumiOpen · 8.0B · runs from 4.0 GB
Llama Poro 2 8B Instruct is a 8.0B-parameter open language model from LumiOpen in the Llama family. It supports a context window of up to 8,192 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qwen3.6 27B Heretic2 Uncensored Finetune Thinking
DavidAU · 27.4B · runs from 12.4 GB
Qwen3.6 27B Heretic2 Uncensored Finetune Thinking is a 27.4B-parameter open language model from DavidAU in the Qwen 3.6 family. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
BananaMind 2 Pro
BananaMind · 160M · runs from 0.7 GB
BananaMind 2 Pro is a 160M-parameter open language model from BananaMind. It supports a context window of up to 3,072 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
MiniCPM MoE 8x2B
OpenBMB · 8x2B · runs from 7.8 GB
MiniCPM MoE 8x2B is a 8x2B-parameter open language model from OpenBMB in the MiniCPM family. It supports a context window of up to 4,096 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
EuroMoE 2.6B A0.6B 2512
utter-project · 2.6B · runs from 1.5 GB
EuroMoE 2.6B A0.6B 2512 is a 2.6B-parameter open language model from utter-project. It supports a context window of up to 4,096 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qwen3.8 27B Obliterated E03
manitcor · 26.9B · runs from 12.2 GB
Qwen3.8 27B Obliterated E03 is a 26.9B-parameter open language model from manitcor in the Qwen 3.8 family. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
SemanticRepair 270M
Gramscii-IT · 268M · runs from 0.4 GB
SemanticRepair 270M is a 268M-parameter open language model from Gramscii-IT. It supports a context window of up to 32,768 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
MedPsy 4B
qvac · 4.4B · runs from 2.4 GB
MedPsy 4B is a 4.4B-parameter open language model from qvac. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
MicroLlama v2
ViorikaAI-org · 45M · runs from 0.3 GB
MicroLlama v2 is a 45M-parameter open language model from ViorikaAI-org in the Llama family. It supports a context window of up to 2,048 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Pythagoras Prover 4B
Pythagoras-LM · 4.4B · runs from 2.4 GB
Pythagoras Prover 4B is a 4.4B-parameter open language model from Pythagoras-LM. It supports a context window of up to 40,960 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Llama 3.2 1B MathCodeInstruct 5k
OliverSundaram · 1.2B · runs from 0.9 GB
Llama 3.2 1B MathCodeInstruct 5k is a 1.2B-parameter open language model from OliverSundaram in the Llama 3 family. It supports a context window of up to 131,072 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Turkish Gemma 9B T1
ytu-ce-cosmos · 9.2B · runs from 4.8 GB
Turkish Gemma 9B T1 is a 9.2B-parameter open language model from ytu-ce-cosmos in the Gemma family. It supports a context window of up to 8,192 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Claim Extractor 4B Q 2605
principled-intelligence · 4.7B · runs from 9.8 GB
Claim Extractor 4B Q 2605 is a 4.7B-parameter open language model from principled-intelligence. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Parable Qwen3 4B Claude Fable 5
AnkitAI · 4.0B · runs from 2.2 GB
Parable Qwen3 4B Claude Fable 5 is a 4.0B-parameter open language model from AnkitAI in the Qwen 3 family. It supports a context window of up to 40,960 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qwopus3.5 4B Coder
Jackrong · 4.7B · runs from 9.8 GB
Qwopus3.5 4B Coder is a 4.7B-parameter open language model from Jackrong. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Param 1 2.9B Instruct
bharatgenai · 2.9B · runs from 6.3 GB
Param 1 2.9B Instruct is a 2.9B-parameter open language model from bharatgenai. It supports a context window of up to 8,192 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Tmax 27B
Allen AI · 26.9B · runs from 12.2 GB
Tmax 27B is Allen AI's largest terminal-agent model, fine-tuned from Qwen 3.6 27B using DPPO, a reinforcement-learning method, to operate as a command-line coding agent rather than a general chat assistant. It is part of a family of terminal agents at 2B, 4B, 9B, and 27B scale, and the vision head from the base model was removed during training since it only handles text. On Terminal Bench 2.0 the card reports roughly 43% pass rate after 160 steps of RL training, ahead of the smaller Tmax variants. At 27B parameters, it needs a multi-GPU setup for full-precision inference, though it fits a single high-end GPU once quantized. The base architecture supports a context length of 262,144 tokens, though training used rollouts capped at 65,536 tokens per episode. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in June 2026.
Open 1B Base
Gensyn · 1.6B · runs from 3.6 GB
Open 1B Base is a 1.6B-parameter open language model from Gensyn. It supports a context window of up to 4,096 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qwen3.5 4B Claude Opus 4.6 Distilled Heretic
ghost-actual · 4.5B · runs from 9.6 GB
Qwen3.5 4B Claude Opus 4.6 Distilled Heretic is a 4.5B-parameter open language model from ghost-actual in the Qwen 3.5 family. It supports a context window of up to 262,144 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
SupraNeo 4M
SupraLabs · 4M · runs from 0.3 GB
SupraNeo 4M is a 4M-parameter open language model from SupraLabs. It supports a context window of up to 1,024 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Speck1 140M Instruct
specklabs · 141M · runs from 0.6 GB
Speck1 140M Instruct is a 141M-parameter open language model from specklabs. It supports a context window of up to 4,096 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.