All LLM Models
Browse 1475 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
Qwen3.8 27B DSpark Agentic
tiyuvta · 27B · runs from 11.8 GB
1.1K
5Qwen3.8 27B DSpark Agentic is a 27B-parameter open language model from tiyuvta 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.
Ternary Bonsai 2 27B Vllm
fraserprice · 3.5B · runs from 7.8 GB
Ternary Bonsai 2 27B Vllm is a 3.5B-parameter open language model from fraserprice. 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.
Phi 4 Mini Flash Reasoning
Microsoft · 3.9B · runs from 2.3 GB
Phi 4 Mini Flash Reasoning is a 3.9B-parameter open language model from Microsoft in the Phi 4 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.
PicoMistral 23M
PicoKittens · 24M · runs from 0.3 GB
PicoMistral 23M is a 24M-parameter open language model from PicoKittens in the Mistral family. It supports a context window of up to 512 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
GLM 4.7 Flash Heretic
Olafangensan · 29.9B · runs from 13.8 GB
GLM 4.7 Flash Heretic is a 29.9B-parameter open language model from Olafangensan in the GLM 4 family. It supports a context window of up to 202,752 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Atria Dawn Preview
InternLM · 753.3B · runs from 1510.9 GB
Atria Dawn Preview is a preview-stage agentic model from the Shanghai Artificial Intelligence Laboratory, built on a 744-billion-parameter Mixture-of-Experts GLM-5.2 foundation. It is an instruction-tuned model designed for research and engineering workflows that require continuous environment understanding, tool use, and multi-step task completion, spanning research-style discovery, building software and applications, producing structured deliverables like reports, and authorized cybersecurity analysis. It supports a 256K token context window and is released under the MIT license. At roughly 744 billion total parameters, local deployment at 4-bit quantization needs several hundred gigabytes of memory, putting it solidly in multi-GPU server territory; most users will reach it through a hosted endpoint rather than local hardware.
Qwen35b Agent R2O3
hotdogs · 34.7B · runs from 15.1 GB
Qwen35b Agent R2O3 is a 34.7B-parameter open language model from hotdogs in the Qwen 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.
GLM 5.3 Flash EXL3 K2
vcruz305 · 48.9B · runs from 22.6 GB
GLM 5.3 Flash EXL3 K2 is a 48.9B-parameter open language model from vcruz305 in the GLM 5 family. It supports a context window of up to 1,048,576 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
LFM2.5 230M Chess
mlabonne · 231M · runs from 0.5 GB
LFM2.5 230M Chess is a 231M-parameter open language model from mlabonne 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.
Ornith 1.5 35B A3B REAP 50 NVFP4A16
Ttimms · 18.5B · runs from 37.5 GB
Ornith 1.5 35B A3B REAP 50 NVFP4A16 is a 18.5B-parameter open language model from Ttimms in the Ornith 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.
Cagliostro V1
bench-labs · 157M · runs from 0.5 GB
Cagliostro V1 is a 157M-parameter open language model from bench-labs. 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.
Trinity Large Preview
Arcee AI · 398.6B · runs from 797.8 GB
Trinity Large Preview is a 398.6B-parameter open language model from Arcee AI. 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.
Qwen 3.5 Sql 27B Distill 2B
AlioLeuchtmann · 27B · runs from 54.4 GB
Qwen 3.5 Sql 27B Distill 2B is a 27B-parameter open language model from AlioLeuchtmann 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.
Qwen3.6 27B M
trymirai · 14.1B · runs from 6.6 GB
Qwen3.6 27B M is a 14.1B-parameter open language model from trymirai in the Qwen 3.6 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qwen3.5 4B EmperoAI Qwen3.8 Distill Heretic Abliterated
insraq · 4.5B · runs from 9.6 GB
Qwen3.5 4B EmperoAI Qwen3.8 Distill Heretic Abliterated is a 4.5B-parameter open language model from insraq 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.
Qwen3.6 28B
0xSero · 28.2B · runs from 12.4 GB
Qwen3.6 28B is a 28.2B-parameter open language model from 0xSero 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.
MiniCPM5 1B CoreAI
mlboydaisuke · 1B · runs from 2.2 GB
MiniCPM5 1B CoreAI is a 1B-parameter open language model from mlboydaisuke in the MiniCPM family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Ice AI
darkps · 8.2B · runs from 4.1 GB
Ice AI is a 8.2B-parameter open language model from darkps. 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.
Gemma 4 12B Agentic Fable5 Composer2.5 v2 3.5x Tau2
yuxinlu1 · 12.0B · runs from 6.1 GB
Gemma 4 12B Agentic Fable5 Composer2.5 v2 3.5x Tau2 is a 12.0B-parameter open language model from yuxinlu1 in the Gemma 4 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.
WaifuGemma4 26B A4b V1
hiwaifu-research · 25.8B · runs from 52.3 GB
WaifuGemma4 26B A4b V1 is a 25.8B-parameter open language model from hiwaifu-research in the Gemma 4 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.
Kumru 2B
vngrs-ai · 2.4B · runs from 1.4 GB
Kumru 2B is a 2.4B-parameter open language model from vngrs-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.
Kumru 2B Base
vngrs-ai · 2.4B · runs from 1.4 GB
Kumru 2B Base is a 2.4B-parameter open language model from vngrs-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.
Turkish Gemma 9B v0.1
ytu-ce-cosmos · 9.2B · runs from 4.8 GB
Turkish Gemma 9B v0.1 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.
Surjo 50M
SurjoLabs · 54M · runs from 0.4 GB
Surjo 50M is a 54M-parameter open language model from SurjoLabs. 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.
Ling 2.6 1T
Inclusion AI · 1025.7B · runs from 2057.0 GB
Ling 2.6 1T is a 1025.7B-parameter open language model from Inclusion AI. 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.
PicoLM 80M Instruct
aethertp · 90M · runs from 0.4 GB
PicoLM 80M Instruct is a 90M-parameter open language model from aethertp. 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.
Supra 50M Base
SupraLabs · 52M · runs from 0.3 GB
Supra 50M Base is a 52M-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.
Ring 2.6 1T
Inclusion AI · 1025.7B · runs from 2057.0 GB
Ring-2.6-1T is Inclusion AI's trillion-parameter mixture-of-experts reasoning model, aimed at agentic workflows rather than plain question answering: multi-step task execution, tool invocation, contextual planning, and long-horizon stability in enterprise and coding scenarios. It exposes a "Reasoning Effort" control with high and xhigh settings, letting developers trade latency for reasoning depth, and was trained with an asynchronous reinforcement-learning architecture combined with the IcePop algorithm, carried over from its predecessor Ring-1T, to stabilize RL training at trillion-parameter scale. With roughly 1 trillion total and 64.5 billion active parameters per token, it needs a multi-GPU server even once quantized. Context length is 131,072 tokens natively, extendable to 262,144 tokens with YaRN scaling. It is released under the MIT license, permitting unrestricted commercial and research use, and was published in May 2026, as a successor to Ring-1T.
T5gemma L L Ul2 IT
Google · 1.2B · runs from 2.7 GB
T5gemma L L Ul2 IT is a 1.2B-parameter open language model from Google in the Gemma family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
CyberStrike OffSec 35B
oyildirim · 35.1B · runs from 15.3 GB
CyberStrike OffSec 35B is a 35.1B-parameter open language model from oyildirim. 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.