▣~/runthismodel▍
daemon okbuild 5a3c91d00:00:00Z
hero://detect·tty0 · runthismodelRTM-CLI v0.42.1 · pid 8841
▍
135/145
models you can run
46.7B
largest · Mixtral 8x7B Inst…
600t/s
median throughput @ Q4_K_M
1.03 TB
curated weights indexed
./models·compatibility matrix · 145/145sorted by fit desc
category
/
grade model params vram fit ↓tok/s weights dl/mo ctxarch
Whisper Tiny English (Quantized)sttfeatured
OpenAI · mit
0.039B0.1GB
██████████████████98%
1008032.2 MB72.9k—whisper
all-MiniLM-L6-v2embed
Sentence Transformers · apache-2.0
0.023B0.1GB
██████████████████98%
1008023.0 MB224.5M256bert
BGE Small EN v1.5embed
BAAI · mit
0.033B0.1GB
██████████████████98%
1008036.8 MB53M512bert
Snowflake Arctic Embed Sembed
Snowflake · apache-2.0
0.033B0.1GB
██████████████████98%
1008036.0 MB40.2k512bert
Piper TTS - Amy (English)tts
Rhasspy · mit
0.02B0.1GB
██████████████████98%
1008063.1 MB0—piper
Piper TTS - Lessac (English)tts
Rhasspy · mit
0.02B0.1GB
██████████████████98%
1008063.2 MB0—piper
Piper TTS - Spanish (MLS)tts
Rhasspy · mit
0.02B0.1GB
██████████████████98%
1008063.1 MB0—piper
Piper TTS - German (Thorsten)tts
Rhasspy · mit
0.02B0.1GB
██████████████████98%
1008063.1 MB0—piper
Piper TTS - Chinese (Huayan)tts
Rhasspy · mit
0.02B0.1GB
██████████████████98%
1008063.2 MB0—piper
Piper TTS - Japanese (Kokoro)tts
Rhasspy · mit
0.02B0.1GB
██████████████████98%
1008063.0 MB0—piper
Piper TTS - Koreantts
Rhasspy · mit
0.02B0.1GB
██████████████████98%
1008063.0 MB0—piper
Piper TTS - Russian (Irina)tts
Rhasspy · mit
0.02B0.1GB
██████████████████98%
1008063.2 MB0—piper
Piper TTS - Portuguese (Faber)tts
Rhasspy · mit
0.02B0.1GB
██████████████████98%
1008063.2 MB0—piper
Piper TTS - Arabic (Kareem)tts
Rhasspy · mit
0.02B0.1GB
██████████████████98%
1008063.2 MB0—piper
Jina Reranker Tiny EN
Jina AI · apache-2.0
0.033B0.1GB
██████████████████98%
1008067.5 MB8k8.2kbert
Whisper Tinystt
OpenAI · mit
0.039B0.2GB
██████████████████98%
1008077.7 MB1.5M—whisper
Whisper Basestt
OpenAI · mit
0.074B0.3GB
██████████████████98%
10080148.0 MB4.6M—whisper
Whisper Base Englishstt
OpenAI · mit
0.074B0.3GB
██████████████████98%
10080148.0 MB23.8k—whisper
Nomic Embed Text v1.5embedfeatured
Nomic AI · apache-2.0
0.137B0.3GB
██████████████████98%
10080146.1 MB17.9M8.2knomic-bert
Piper TTS - French (Siwis)tts
Rhasspy · mit
0.02B0.5GB
██████████████████97%
1008028.1 MB0—piper
Piper TTS - Italian (Riccardo)tts
Rhasspy · mit
0.02B0.5GB
██████████████████97%
1008028.1 MB0—piper
Piper TTS - LibriTTS-R (English)tts
Rhasspy · mit
0.02B0.6GB
██████████████████97%
1008078.6 MB0—piper
Kokoro 82M TTSttsfeatured
Kokoro · apache-2.0
0.082B0.6GB
██████████████████97%
1008086.0 MB517.4k—kokoro
SmolLM2 135M
HuggingFace · apache-2.0
0.135B0.6GB
██████████████████97%
10080144.8 MB1.7M8.2ksmollm
SmolLM2 360M
HuggingFace · apache-2.0
0.36B0.8GB
██████████████████97%
5000270.6 MB283.9k8.2ksmollm
MusicGen Smalltts
Meta · cc-by-nc-4.0
0.3B0.8GB
█████████████████░97%
6000302.4 MB197.6k—musicgen
Danube 3 500M
H2O.ai · apache-2.0
0.5B0.8GB
█████████████████░97%
3600317.9 MB31.1k8.2kdanube
BGE Large EN v1.5embed
BAAI · mit
0.335B0.8GB
█████████████████░97%
5373358.2 MB13.8M512bert
Whisper Smallstt
OpenAI · mit
0.24B0.9GB
█████████████████░97%
7500487.6 MB2.4M—whisper
Qwen 2.5 0.5B
Alibaba · apache-2.0
0.5B1.0GB
█████████████████░97%
3600491.4 MB4.2M32.8kqwen2
TinyLlama 1.1B
TinyLlama · apache-2.0
1.1B1.1GB
█████████████████░97%
1636668.8 MB2M2kllama
Qwen 2.5 Coder 0.5Bcode
Alibaba · apache-2.0
0.5B1.1GB
█████████████████░97%
3600675.7 MB99.1k32.8kqwen2
Llama 3.2 1B Instructfeatured
Meta · llama3.2
1.24B1.3GB
█████████████████░97%
1452807.7 MB7.4M131.1kllama
Gemma 3 1Bfeatured
Google · gemma
1B1.3GB
█████████████████░97%
1800806.1 MB1.8M32.8kgemma3
Granite 3.0 1B-A400Mmoe·0.4b act
IBM · apache-2.0
1.3B1.3GB
█████████████████░97%
4500821.8 MB8784.1kgranitemoe
DeepSeek Coder 1.3Bcode
DeepSeek · mit
1.3B1.3GB
█████████████████░97%
1385873.6 MB43.3k16.4kllama
Yi Coder 1.5Bcode
01.AI · apache-2.0
1.5B1.4GB
█████████████████░97%
1200963.7 MB5.1k4.1kyi
Qwen2-VL 2Bvlm
Alibaba · apache-2.0
2.2B1.4GB
█████████████████░97%
818986.0 MB3.7M32.8kqwen2-vl
SmolLM2 1.7B
HuggingFace · apache-2.0
1.7B1.5GB
█████████████████░97%
10591.06 GB163.4k8.2ksmollm
Falcon 3 1B
TII · apache-2.0
1B1.5GB
█████████████████░97%
18001.06 GB9.9k8.2kfalcon
Moondream 2vlmfeatured
Moondream · apache-2.0
1.8B1.5GB
█████████████████░97%
10001.00 GB1.9M2kmoondream
Qwen 2.5 1.5B
Alibaba · apache-2.0
1.5B1.5GB
█████████████████░96%
12001.12 GB10.7M32.8kqwen2
DeepSeek R1 Distill 1.5B
DeepSeek · mit
1.5B1.5GB
█████████████████░96%
12001.12 GB681.8k131.1kqwen2
Qwen 2.5 Coder 1.5Bcode
Alibaba · apache-2.0
1.5B1.5GB
█████████████████░96%
12001.12 GB748.8k32.8kqwen2
Stable Diffusion 2.1 Base (CoreML)imagefeatured
Stability AI / Apple · creativeml-openrail-m
0.86B1.6GB
█████████████████░96%
20931.14 GB40—unet-diffusion
BGE Reranker v2 M3
BAAI · mit
0.568B1.6GB
█████████████████░96%
31691.16 GB14.1M8.2kxlm-roberta
Distil-Whisper Large v3sttfeatured
HuggingFace · mit
0.76B1.9GB
█████████████████░96%
23681.52 GB869.8k—whisper
Whisper Mediumsttfeatured
OpenAI · mit
0.77B1.9GB
█████████████████░96%
23381.53 GB475.7k—whisper
Granite 3.3 2B
IBM · apache-2.0
2B1.9GB
█████████████████░96%
9001.55 GB21.9k8.2kgranite
Whisper Large v3 Turbosttfeatured
OpenAI · mit
0.81B2.0GB
█████████████████░96%
22221.62 GB7.7M—whisper
CodeGemma 2Bcode
Google · gemma
2B2.0GB
█████████████████░96%
9001.63 GB31k8.2kgemma
EXAONE 3.5 2.4B
LG AI · other
2.4B2.0GB
█████████████████░96%
7501.64 GB63.8k32.8kexaone
Gemma 2 2B
Google · gemma
2.6B2.1GB
█████████████████░96%
6921.71 GB315.4k8.2kgemma2
StableLM Zephyr 3B
Stability AI · other
3B2.1GB
█████████████████░96%
6001.71 GB28.4k4.1kstablelm
Rocket 3B
Pansophic · other
3B2.1GB
█████████████████░96%
6001.71 GB4204.1kstablelm
Stable Code 3Bcode
Stability AI · other
3B2.1GB
█████████████████░96%
6001.71 GB2.2k16.4kstablelm
MiniCPM-V 2.6vlm
OpenBMB · apache-2.0
2B2.1GB
█████████████████░96%
9001.60 GB151.6k2kminicpm-v
Stable Diffusion 1.5 (GGUF)imagefeatured
Runway / GPUStack · creativeml-openrail-m
0.86B2.1GB
█████████████████░96%
20931.75 GB1.3k—unet-diffusion
StarCoder2 3Bcode
BigCode · bigcode-openrail-m
3B2.3GB
█████████████████░96%
6001.89 GB123k16.4kstarcoder
Falcon 3 3B
TII · apache-2.0
3B2.4GB
█████████████████░96%
6002.01 GB6.2k8.2kfalcon
Llama 3.2 3B Instructfeatured
Meta · llama3.2
3.2B2.4GB
█████████████████░96%
5622.02 GB1.4M131.1kllama
Granite 3.0 3B-A800Mmoe·0.8b act
IBM · apache-2.0
3.4B2.4GB
█████████████████░96%
22502.06 GB3.4k4.1kgranitemoe
Qwen 2.5 3B
Alibaba · apache-2.0
3B2.5GB
█████████████████░96%
6002.10 GB12.7M32.8kqwen2
Qwen 2.5 Coder 3Bcode
Alibaba · apache-2.0
3B2.5GB
█████████████████░96%
6002.10 GB229.1k32.8kqwen2
Stable Diffusion 1.5 (CoreML)image
Runway · creativeml-openrail-m
0.86B2.5GB
█████████████████░96%
20931.57 GB1.6M—unet-diffusion
PaliGemma 3Bvlm
Google · gemma
3B2.5GB
█████████████████░96%
6002.00 GB198.8k256paligemma
Stable Diffusion 2.1 (GGUF)image
Stability AI · creativeml-openrail-m
0.86B2.7GB
█████████████████░95%
20932.32 GB——unet-diffusion
Phi-3.5 Mini 3.8Bfeatured
Microsoft · mit
3.8B2.7GB
█████████████████░95%
4742.39 GB901.4k131.1kphi3
Danube 3 4B
H2O.ai · apache-2.0
4B2.7GB
█████████████████░95%
4502.39 GB4298.2kdanube
Gemma 3 4Bfeatured
Google · gemma
4B2.8GB
█████████████████░95%
4502.49 GB1.5M32.8kgemma3
Phi-4 Mini 3.8Bfeatured
Microsoft · mit
3.8B2.8GB
█████████████████░95%
4742.49 GB1.1M131.1kphi4
Nemotron Mini 4B
NVIDIA · other
4B3.0GB
█████████████████░95%
4502.70 GB421k8.2knemotron
Phi-3.5 Visionvlmfeatured
Microsoft · mit
4.2B3.2GB
█████████████████░95%
4292.50 GB2M131.1kphi3v
Stable Diffusion XL (CoreML)imagefeatured
Stability AI · creativeml-openrail-m
3.5B3.3GB
█████████████████░95%
5143.05 GB1.4M—unet-diffusion
Whisper Large v3sttfeatured
OpenAI · mit
1.55B3.4GB
█████████████████░95%
11613.10 GB5.1M—whisper
Yi 1.5 6B Chat
01.AI · apache-2.0
6B3.9GB
█████████████████░94%
3003.67 GB5.9k4.1kyi
DeepSeek Coder 6.7Bcode
DeepSeek · mit
6.7B4.3GB
█████████████████░94%
2694.08 GB143.7k16.4kllama
Code Llama 7Bcode
Meta · llama2
7B4.3GB
█████████████████░94%
2574.08 GB244.6k16.4kllama
OLMoE 1B-7Bfeaturedmoe·1.3b act
AI2 · apache-2.0
6.9B4.4GB
█████████████████░94%
13854.21 GB37k4.1kolmoe
Mistral 7B Instruct v0.3featured
Mistral AI · apache-2.0
7.3B4.6GB
█████████████████░93%
2474.37 GB3.1M32.8kmistral
OpenChat 3.5 7B
OpenChat · apache-2.0
7B4.6GB
█████████████████░93%
2574.37 GB4.9k8.2kmistral
StarCoder2 7Bcode
BigCode · bigcode-openrail-m
7B4.7GB
█████████████████░93%
2574.46 GB12.3k16.4kstarcoder
OLMo 2 7B
Allen AI · apache-2.0
7B4.7GB
█████████████████░93%
2574.47 GB49.4k4.1kolmo
Qwen 2.5 Coder 7Bcodefeatured
Alibaba · apache-2.0
7.6B4.9GB
█████████████████░93%
2374.68 GB2.1M32.8kqwen2
InternLM 2.5 7B
Shanghai AI Lab · apache-2.0
7.7B4.9GB
█████████████████░93%
2344.71 GB109.7k32.8kinternlm2
EXAONE 3.5 7.8B
LG AI · other
7.8B4.9GB
█████████████████░93%
2314.77 GB139.5k32.8kexaone
LLaVA 1.6 7Bvlmfeatured
LLaVA · apache-2.0
7B5.0GB
█████████████████░93%
2574.40 GB705.7k4.1kllava
Falcon 3 7B
TII · apache-2.0
7B5.0GB
█████████████████░93%
2574.40 GB9.7k8.2kfalcon
SDXL Turbo (GGUF)imagefeatured
Stability AI · stability-community
3.5B5.0GB
█████████████████░93%
5143.50 GB783.7k—unet-diffusion
DeepSeek R1 Distill 8Bfeatured
DeepSeek · mit
8B5.1GB
█████████████████░93%
2254.92 GB439k131.1kllama
Llama 3.1 8B Instructfeatured
Meta · llama3.1
8B5.1GB
█████████████████░93%
2254.92 GB9.9M131.1kllama
Dolphin 3.0 Llama 3.1 8B
Cognitive Computations · llama3.1
8B5.1GB
█████████████████░93%
2254.92 GB360.8k131.1kllama
NeuralDaredevil 8B (abliterated)
mlabonne · llama3
8B5.1GB
█████████████████░93%
2254.92 GB13.5k8.2kllama
Llama 3.1 8B Instruct (abliterated)
mlabonne · llama3.1
8B5.1GB
█████████████████░93%
2254.92 GB4.4k131.1kllama
Stheno L3 8B v3.2
Sao10K · cc-by-nc-4.0
8B5.1GB
█████████████████░93%
2254.92 GB13.4k8.2kllama
Granite 3.3 8B
IBM · apache-2.0
8B5.1GB
█████████████████░93%
2254.94 GB62.1k8.2kgranite
Qwen 2.5 7B Instructfeatured
Alibaba · apache-2.0
7.6B5.3GB
█████████████████░93%
2374.70 GB11.9M131.1kqwen2
Qwen3 8B Basefeatured
Alibaba · apache-2.0
8B5.3GB
█████████████████░93%
2254.80 GB453.7k32.8kqwen3
CodeGemma 7Bcode
Google · gemma
8.5B5.5GB
█████████████████░93%
2125.33 GB2.6k8.2kgemma
Yi 1.5 9B Chat
01.AI · apache-2.0
9B5.5GB
█████████████████░93%
2005.33 GB18.2k4.1kyi
Yi Coder 9Bcode
01.AI · apache-2.0
9B5.5GB
█████████████████░93%
2005.33 GB8.9k4.1kyi
Gemma 2 9B Instructfeatured
Google · gemma
9.2B5.9GB
█████████████████░92%
1965.76 GB391k8.2kgemma2
Stable Audio Opentts
Stability AI · stability-community
1B6.0GB
█████████████████░92%
18002.50 GB43k—stable-audio
Falcon 3 10B
TII · apache-2.0
10B6.4GB
████████████████░░92%
1806.29 GB4.4k8.2kfalcon
Solar 10.7B
Upstage · apache-2.0
10.7B6.5GB
████████████████░░91%
1686.46 GB52.1k4.1kllama
Gemma 3 MoE 9Bmoe·2.5b act
Google · gemma
9B7.0GB
████████████████░░91%
7205.50 GB—8.2kgemma3-moe
Gemma 3 12Bfeatured
Google · gemma
12B7.3GB
████████████████░░91%
1507.30 GB2.6M32.8kgemma3
Mistral Nemo 12Bfeatured
Mistral AI · apache-2.0
12B7.5GB
████████████████░░91%
1507.48 GB451.4k131.1kmistral
Magnum v4 12B
Anthracite · apache-2.0
12B7.5GB
████████████████░░91%
1507.48 GB686131.1kmistral
Rocinante 12B v1.1
TheDrummer · other
12B7.5GB
████████████████░░91%
1507.48 GB811131.1kmistral
Mistral Nemo Base 12Bfeatured
Mistral AI · apache-2.0
12B7.7GB
████████████████░░90%
1507.20 GB29.7k131.1kmistral
Code Llama 13B Instructcode
Meta · llama2
13B7.8GB
████████████████░░90%
1387.87 GB2.7k16.4kllama
ACE-Step 1.5XLttsfeatured
ACE Studio · apache-2.0
1.5B8.0GB
████████████████░░90%
12003.00 GB——acestep
Qwen 2.5 14Bfeatured
Alibaba · apache-2.0
14B8.9GB
████████████████░░89%
1298.99 GB1.9M131.1kqwen2
Qwen 2.5 Coder 14Bcodefeatured
Alibaba · apache-2.0
14B8.9GB
████████████████░░89%
1298.99 GB3M32.8kqwen2
Phi-4featured
Microsoft · mit
14B8.9GB
████████████████░░89%
1299.05 GB814.3k16.4kphi3
Stable Diffusion 3 Medium (GGUF)imagefeatured
Stability AI · stability-community
2.5B9.2GB
████████████████░░89%
7209.29 GB3.1k—mmdit-diffusion
Rocinante XL 16B v1
TheDrummer · other
16B9.6GB
████████████████░░88%
1129.75 GB68131.1kmistral
DeepSeek MoE 16Bmoe·2.8b act
DeepSeek · other
16.4B11.0GB
████████████████░░87%
6439.50 GB14.3k4.1kdeepseek-moe
TRELLIS Image Largeimagefeatured
Microsoft · mit
1.2B12.0GB
███████████████░░░86%
15002.40 GB1.2M—trellis
Mistral Small 22B
Mistral AI · apache-2.0
22B12.9GB
███████████████░░░83%
8213.34 GB127.5k32.8kmistral
Codestral 22B (abliterated)code
failspy · other
22B12.9GB
███████████████░░░83%
8213.34 GB7.5k32.8kmistral
Magnum v4 22B
Anthracite · other
22B12.9GB
███████████████░░░83%
8213.34 GB24832.8kmistral
Dolphin 3.0 R1 Mistral 24Bfeatured
Cognitive Computations · apache-2.0
24B13.8GB
██████████████░░░░80%
7514.33 GB686131.1kmistral
Cydonia 24B v4.3
TheDrummer · other
24B13.8GB
██████████████░░░░80%
7514.33 GB6k32.8kmistral
FLUX.1 Schnell (GGUF)imagefeatured
Black Forest Labs · apache-2.0
12B14.0GB
██████████████░░░░79%
15012.00 GB301.4k—rectified-flow
FLUX.1 Dev (GGUF)image
Black Forest Labs · flux-1-dev-non-commercial
12B14.0GB
██████████████░░░░79%
15012.00 GB1.1M—rectified-flow
Dolphin Mistral 24B (Venice Edition)featured
Cognitive Computations · apache-2.0
24B14.9GB
██████████████░░░░76%
7514.40 GB7.8k32.8kmistral
Gemma 3 27Bfeatured
Google · gemma
27B15.9GB
█████████████░░░░░73%
6716.55 GB1.4M32.8kgemma3
Wan 2.2 TI2V 5Bimagefeatured
Wan-AI · apache-2.0
5B16.0GB
█████████████░░░░░73%
36010.00 GB8.3k—wan-dit
CogVideoX 5Bimage
THUDM · apache-2.0
5B16.0GB
█████████████░░░░░73%
36010.00 GB16.8k—cogvideox
Hunyuan3D 2image
Tencent · tencent-hunyuan
2.5B16.0GB
█████████████░░░░░73%
7205.00 GB76.1k—hunyuan3d
Skyfall 31B v4.2
TheDrummer · other
31B18.2GB
████████████░░░░░░65%
5818.98 GB1k131.1kmistral
Qwen 2.5 32B
Alibaba · apache-2.0
32B19.0GB
███████████░░░░░░░62%
5619.85 GB1M131.1kqwen2
Qwen3 30B-A3Bfeaturedmoe·3.3b act
Alibaba · apache-2.0
30.5B20.0GB
██████████░░░░░░░░58%
54518.00 GB—32.8kqwen3-moe
Phi-3.5 MoEfeaturedmoe·6.6b act
Microsoft · mit
41.9B24.1GB
███████░░░░░░░░░░░38%
27225.35 GB123.9k131.1kphimoe
Mixtral 8x7B Instructfeaturedmoe·12.9b act
Mistral AI · apache-2.0
46.7B25.1GB
██████░░░░░░░░░░░░32%
13426.44 GB806.7k32.8kmixtral
Mochi 1 Previewimage
Genmo · apache-2.0
10B30.0GB
████░░░░░░░░░░░░░░21%
offload20.00 GB3.5k—asymdit
Llama 3.1 70B Instructfeatured
Meta · llama3.1
70B40.1GB
██░░░░░░░░░░░░░░░░10%
offload42.52 GB630.4k131.1kllama
Euryale L3.3 70B v2.3featured
Sao10K · llama3
70B40.1GB
██░░░░░░░░░░░░░░░░10%
offload42.52 GB1.4k131.1kllama
Llama 3.1 70B (lorablated)
mlabonne · llama3.1
70B40.1GB
██░░░░░░░░░░░░░░░░10%
offload42.52 GB57131.1kllama
Magnum v4 72B
Anthracite · apache-2.0
72B44.7GB
██░░░░░░░░░░░░░░░░9%
offload47.42 GB764131.1kqwen2
HunyuanVideo 13Bimagefeatured
Tencent · tencent-hunyuan
13B60.0GB
█░░░░░░░░░░░░░░░░░5%
offload26.00 GB924—hunyuan-dit
Qwen3 235B-A22Bmoe·22b act
Alibaba · apache-2.0
235B144.0GB
░░░░░░░░░░░░░░░░░░2%
offload140.00 GB—32.8kqwen3-moe
Mixtral 8x22B Instructmoe·39.1b act
Mistral AI · apache-2.0
141B88.0GB
░░░░░░░░░░░░░░░░░░2%
offload85.00 GB32.6k65.5kmixtral
distribution·vram footprint × Q4_K_Myour gpu cap: 24 GB
0 – 2 GB█████████████████████████████████████···49
2 – 6 GB████████████████████████████████████████53
6 – 12 GB█████████████···························17
12 – 24 GB████████████····························16
24 – 48 GB█████···································7
48+ GB██······································3
fits tight overflowcutoff @ 24 GB
activity·tail -f /var/log/rtm.loglive
14:02:11MODELqwen3-30b-a3b · +12.4k DL/24h+3s
14:01:48BENCHRTX 5090 · llama-3.1-8b · 142 t/s+10s
13:58:02ADDcandidates.json +3 (deepseek-r2)+17s
13:54:30SYNCHF metadata · 144/145 ok+24s
13:51:09WARNflux-dev · NC license · review+31s
13:47:55SCAN10.7.91.* · M4 Pro · 18GB unified+38s
13:45:01BENCHM3 Max · gemma-3-12b · 28 t/s+45s
13:43:22MODELwhisper-v3-turbo · 1.2M DL/wk+52s
13:39:10FAILgpu probe · WebGPU unavailable+59s
13:36:44SCAN23.51.18.* · RTX 4090 · 24GB+6s
© runthismodel · 2026privacytermsdisclaimercontacteditorial standardschangelogembed badgerunpodvast.aihuggingfaceollamalm-studiomade for the people who actually read GGUF metadata
 ┌─┐                ╔══╗     ╔══╗
 │░│  RUN  THIS  M  ║▓▓║ DEL ║▓▓║
 └─┘                ╚══╝     ╚══╝