All LLM Models
Browse 1214 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
YuE2 3B OrbitQuant W4A4
WaveCut · 2.2B · runs from 5.0 GB
3.1K
5YuE2 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.
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.
Mistral Nemo 2407 12B Thinking Claude Gemini GPT5.2 Uncensored HERETIC
DavidAU · 12.2B · runs from 5.9 GB
Mistral Nemo 2407 12B Thinking Claude Gemini GPT5.2 Uncensored HERETIC is a 12.2B-parameter open language model from DavidAU in the Mistral family. It supports a context window of up to 1,024,000 tokens. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qwen35B Agent R2
hotdogs · 34.7B · runs from 15.1 GB
Qwen35B Agent R2 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.
SpatialLM1.1 Qwen 0.5B
manycore-research · 604M · runs from 1.5 GB
SpatialLM1.1 Qwen 0.5B is a 604M-parameter open language model from manycore-research in the Qwen family. 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.
Qwen3.5 2B Claude 4.6 Opus Reasoning Distilled
Jackrong · 2.3B · runs from 1.4 GB
Qwen3.5 2B Claude 4.6 Opus Reasoning Distilled is a 2.3B-parameter open language model from Jackrong 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.
Thinkless 1.5B RL DeepScaleR
Vinnnf · 1.8B · runs from 1.1 GB
Thinkless 1.5B RL DeepScaleR is a 1.8B-parameter open language model from Vinnnf. 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.
LFM2 1.2B Extract
Liquid AI · 1.2B · runs from 0.9 GB
LFM2 1.2B Extract is a 1.2B-parameter open language model from Liquid AI in the LFM2 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.
Qwen3.5 4B Safety Thinking
MerlinSafety · 4.2B · runs from 2.3 GB
Qwen3.5 4B Safety Thinking is a 4.2B-parameter open language model from MerlinSafety 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.
Bonsai 2 27B Mtp
decent-jawfish · 27B · runs from 12.6 GB
Bonsai 2 27B Mtp is a 27B-parameter open language model from decent-jawfish. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Qwen3.5 4B Claude 4.6 Opus Reasoning Distilled
Jackrong · 4.7B · runs from 2.5 GB
Qwen3.5 4B Claude 4.6 Opus Reasoning Distilled is a 4.7B-parameter open language model from Jackrong 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.
OmniSVG1.1 8B
OmniSVG · 8B · runs from 16.4 GB
OmniSVG1.1 8B is a 8B-parameter open language model from OmniSVG. 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.
Codegemma 7B IT
Google · 8.5B · runs from 4.0 GB
Codegemma 7B IT is a 8.5B-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.
Qwythos 9B v2
empero-ai · 9.7B · runs from 19.9 GB
Qwythos 9B v2 is a 9.7B-parameter open language model from empero-ai. 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.
Gemma4 12B Mtp Assistant
sjakek · 12B · runs from 5.6 GB
Gemma4 12B Mtp Assistant is a 12B-parameter open language model from sjakek in the Gemma 4 family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
QU SSM 130M MoE
Prannesshkva · 135M · runs from 0.3 GB
QU SSM 130M MoE is a 135M-parameter open language model from Prannesshkva. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.
Claude OSS
squ11z1 · 9.0B · runs from 4.4 GB
Claude OSS is a 9.0B-parameter open language model from squ11z1. 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.
Nemotron Research Reasoning Qwen 1.5B
NVIDIA · 1.8B · runs from 1.1 GB
Nemotron Research Reasoning Qwen 1.5B is a 1.8B-parameter open language model from NVIDIA in the Qwen 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.
Llama3 OpenBioLLM 8B
aaditya · 8B · runs from 4.0 GB
Llama3 OpenBioLLM 8B is a 8B-parameter open language model from aaditya in the Llama 3 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.
Internlm 7B
InternLM · 7B · runs from 15.4 GB
InternLM-7B is InternLM's open base pretrained language model, not instruction-tuned, built at 7 billion parameters and trained on trillions of high-quality tokens to serve as a general-purpose knowledge foundation for downstream fine-tuning. On the OpenCompass evaluation suite it outperformed same-size peers such as LLaMA-7B and Baichuan-7B across disciplinary, language, knowledge, reasoning, and comprehension benchmarks. A matching InternLM-Chat-7B instruction-tuned version was released alongside it. Its 7B size fits on a single consumer GPU. Context length is 2,048 tokens. The code is released under Apache 2.0, while the model weights are free for academic research and free for commercial use only after completing InternLM's application form. It was published in July 2023, as InternLM's first open base model; larger InternLM2 and later families followed.
MeoinGTS1.5 1.5B
ali-arshiya · 494M · runs from 0.5 GB
MeoinGTS1.5 1.5B is a 494M-parameter open language model from ali-arshiya. 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.
Maple Preview
deepgrove · 20.2B · runs from 9.0 GB
Maple Preview is a 20.2B-parameter open language model from deepgrove. 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.
OpenGuardrails Text 2510
openguardrails · 14.8B · runs from 6.9 GB
OpenGuardrails Text 2510 is a 14.8B-parameter open language model from openguardrails. 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.
Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM
Ex0bit · 30B · runs from 14.0 GB
Elbaz NVIDIA Nemotron 3 Nano 30B A3B PRISM is a 30B-parameter open language model from Ex0bit in the Nemotron family. See its VRAM requirements by quantization and which GPUs and Macs can run it locally below.