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
Polyglot Ko 1.3B
EleutherAI · 1.4B · runs from 0.7 GB
3.9K
92Polyglot Ko 1.3B is a 1.4B-parameter open language model from EleutherAI. 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.
MythoMax L2 13B
Gryphe · 13B · runs from 7.5 GB
MythoMax L2 13B is a 13B-parameter open language model from Gryphe. 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 Escha W2
EschaLabs · 6.3B · runs from 13.4 GB
Qwen3.8 27B Escha W2 is a 6.3B-parameter open language model from EschaLabs 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.
Huihui CyberStrike OffSec 35B Abliterated
huihui-ai · 36.0B · runs from 15.7 GB
Huihui CyberStrike OffSec 35B Abliterated is a 36.0B-parameter open language model from huihui-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.
Bella Bartender 8B Llama3.1
juiceb0xc0de · 8.0B · runs from 3.0 GB
Bella Bartender 8B Llama3.1 is a 8.0B-parameter open language model from juiceb0xc0de 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.
KONI Llama3.1 8B Instruct 20241024
KISTI-KONI · 8.0B · runs from 4.0 GB
KONI Llama3.1 8B Instruct 20241024 is a 8.0B-parameter open language model from KISTI-KONI 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.
Saul 7B Instruct V1
Equall · 7.2B · runs from 3.6 GB
Saul 7B Instruct V1 is a 7.2B-parameter open language model from Equall. 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.
Cali 0.1B
Sandroeth · 124M · runs from 0.3 GB
Cali 0.1B is a 124M-parameter open language model from Sandroeth. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
DeepSeek V4 Flash JANG CRACK
dealignai · 33.5B · runs from 14.6 GB
DeepSeek V4 Flash JANG CRACK is a 33.5B-parameter open language model from dealignai in the DeepSeek V4 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.
Qwen3 4B Gemini 3.1 Pro Reasoning Distilled
khazarai · 4B · runs from 2.2 GB
Qwen3 4B Gemini 3.1 Pro Reasoning Distilled is a 4B-parameter open language model from khazarai in the Qwen 3 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.
Humanizer Gemma 4 E4b
jialinyyzz · 7.9B · runs from 3.9 GB
Humanizer Gemma 4 E4b is a 7.9B-parameter open language model from jialinyyzz in the Gemma 4 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.
MiniCPM5 2B Midtrain
OpenBMB · 2.5B · runs from 1.5 GB
MiniCPM5 2B Midtrain is a 2.5B-parameter open language model from OpenBMB in the MiniCPM 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.
OpenMath Nemotron 1.5B
NVIDIA · 1.5B · runs from 1.0 GB
OpenMath Nemotron 1.5B is a 1.5B-parameter open language model from NVIDIA in the Nemotron 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.
Ssiat 1.0
MOGODIK · 255M · runs from 0.5 GB
Ssiat 1.0 is a 255M-parameter open language model from MOGODIK. 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.
Qwen3 4B Instruct 2507 Heretic
p-e-w · 4.0B · runs from 2.2 GB
Qwen3 4B Instruct 2507 Heretic is a 4.0B-parameter open language model from p-e-w in the Qwen 3 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.
Bielik 4.5B V3.0 Instruct
speakleash · 4.8B · runs from 10.5 GB
Bielik 4.5B V3.0 Instruct is a 4.8B-parameter open language model from speakleash. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
TildeOpen 30B
TildeAI · 30.7B · runs from 13.8 GB
TildeOpen 30B is a 30.7B-parameter open language model from TildeAI. It supports a context window of up to 65,536 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
MiroThinker 1.7 Mini
miromind-ai · 30.5B · runs from 13.4 GB
MiroThinker 1.7 Mini is a 30.5B-parameter open language model from miromind-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.
G9v3 3B
ai9stars · 3.0B · runs from 1.7 GB
G9v3 3B is a 3.0B-parameter open language model from ai9stars. 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.
Qwen3.6 40B Deckard MTP
PiehSoft · 40B · runs from 18.7 GB
Qwen3.6 40B Deckard MTP is a 40B-parameter open language model from PiehSoft in the Qwen 3.6 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Instella MoE 16B A3B Think
amd · 15.9B · runs from 7.5 GB
Instella MoE 16B A3B Think is a 15.9B-parameter open language model from amd. 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.
YuE2 3B OrbitQuant W4A4
WaveCut · 2.2B · runs from 5.0 GB
YuE2 3B OrbitQuant W4A4 is a 2.2B-parameter open language model from WaveCut. It supports a context window of up to 24,576 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qwen3.8 27B EXL3 3.5bpw
Mia-AiLab · 7.7B · runs from 16.1 GB
Qwen3.8 27B EXL3 3.5bpw is a 7.7B-parameter open language model from Mia-AiLab 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.
BitCPM CANN 8B
OpenBMB · 8B · runs from 3.8 GB
BitCPM-CANN-8B is OpenBMB's 8-billion-parameter ternary (1.58-bit) quantization-aware variant of its MiniCPM4-8B model, produced by the first publicly reported end-to-end 1.58-bit training system built natively for Huawei's Ascend NPU stack, integrating quantization-aware training into Megatron-LM with MindSpeed acceleration. Against its full-precision MiniCPM4-8B counterpart across 11 benchmarks it retains about 95.7% of performance, and the ternary training approach itself adds only a few percent training overhead on Ascend 910B hardware. This particular checkpoint ships in a "pseudo-quantized" format, with ternary values stored as ordinary floating-point weights, so despite the ternary training it loads and runs exactly like the full-precision 8B model rather than at reduced memory, and needs the same hardware as a dense 8B model to run locally. Context length is 32,768 tokens. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in May 2026, alongside smaller 0.5B, 1B, and 3B siblings in the same BitCPM-CANN family.
BAAR2 150M
aixk · 168M · runs from 0.4 GB
BAAR2 150M is a 168M-parameter open language model from aixk. 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.
OxCoder 9B
OrionLLM · 9.4B · runs from 19.4 GB
OxCoder 9B is a 9.4B-parameter open language model from OrionLLM. 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.
AI21 Jamba Reasoning 3B
AI21 Labs · 3.2B · runs from 1.7 GB
AI21 Jamba Reasoning 3B is a 3.2B-parameter open language model from AI21 Labs in the Jamba 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 VL 8B Heretic 1.3.0
DreamFast · 8.8B · runs from 4.3 GB
Qwen3 VL 8B Heretic 1.3.0 is a 8.8B-parameter open language model from DreamFast in the Qwen 3 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.
Mellum2 12B A2.5B Base
JetBrains · 12.1B · runs from 24.7 GB
Mellum2 12B A2.5B Base is a 12.1B-parameter open language model from JetBrains in the Mellum 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.
OpenThinker3 1.5B
open-thoughts · 1.5B · runs from 1.0 GB
OpenThinker3 1.5B is a 1.5B-parameter open language model from open-thoughts. 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.