Discrete GPUNVIDIA
RTX PRO 6000
NVIDIA RTX PRO 6000 Blackwell 96GB
Used across local.ai for this visit
Price
$16.3k
Memory
96 GB
Power Draw
378 W ± 52 W
Price history
Jun 2025–Oct 2026
$16,268.99
CDW (US)Unobserved span
Intelligence / Speed Frontier
local.ai intelligence index
- 81%Qwen 3.8 27B
- 74%Qwen3.6 27B
- 74%Qwen3.6 27B
- 70%Qwen3.6 35B A3B
- 70%Qwen3.6 35B A3B
- 69%Qwen3.6 35B A3B
- 69%Qwen3.6 35B A3B
- 67%
Ornith 1.0 35B - 59%Gemma 4 31B It
- 58%NVIDIA Nemotron 3 Super 120B A12B
- 56%Gpt Oss 120B
- 53%
Holo 3.1 35B A3B - 38%NVIDIA Nemotron 3 Nano 30B A3B
- 29%Gemma 4 E4B It
- 25%Gemma 4 E4B It
- 18%Gemma 4 E2B It
- 13%LFM2.5 8B A1B
- 10%LFM2.5 8B A1B
Tasks per hour
- 700/hLFM2.5 8B A1B
- 651/hLFM2.5 8B A1B
- 425/hGemma 4 E2B It
- 297/hGemma 4 E4B It
- 241/hGemma 4 E4B It
- 109/hNVIDIA Nemotron 3 Nano 30B A3B
- 99/hHolo 3.1 35B A3B
- 82/hGpt Oss 120B
- 75/hOrnith 1.0 35B
- 51/hQwen3.6 35B A3B
- 50/hQwen3.6 35B A3B
- 48/hQwen3.6 35B A3B
- 39/hNVIDIA Nemotron 3 Super 120B A12B
- 36/hQwen3.6 35B A3B
- 36/hGemma 4 31B It
- 26/hQwen3.6 27B
- 20/hQwen3.6 27B
- 12/hQwen 3.8 27B
Models that run on RTX PRO 6000
Qwen 3.8 27B3
Qwen 3.8 27B
Quant fp8 · Reasoning · Medium
Qwen/Qwen3.8-27B-FP8- Intelligence
- 81%
- Task Time
- 4m 51s
- Intelligence / Joule
- 0.80
- Disk Size
- 30.9GB
- Power Draw
- 346W
Qwen 3.8 27B
Quant fp8 · Reasoning · XHigh
Qwen/Qwen3.8-27B-FP8- Intelligence
- 80%
- Task Time
- 6m 33s
- Intelligence / Joule
- 0.59
- Disk Size
- 30.9GB
- Power Draw
- 347W
Qwen 3.8 27B
Quant fp8 · Reasoning · Low
Qwen/Qwen3.8-27B-FP8- Intelligence
- 80%
- Task Time
- 5m 19s
- Intelligence / Joule
- 0.72
- Disk Size
- 30.9GB
- Power Draw
- 347W
Qwen3.6 27B9
Qwen3.6 27B
unsloth/Qwen3.6-27B-MTP-GGUF
Quant Q4_K_M
unsloth/Qwen3.6-27B-MTP-GGUF- Intelligence
- 74%
- Task Time
- 2m 56s
- Intelligence / Joule
- 0.76
- Disk Size
- 17.1GB
- Power Draw
- 553W
Qwen3.6 27B
Quant fp8
Qwen/Qwen3.6-27B-FP8- Intelligence
- 74%
- Task Time
- 2m 21s
- Intelligence / Joule
- 1.60
- Disk Size
- 30.9GB
- Power Draw
- 328W
Qwen3.6 27B
Quant —
Qwen/Qwen3.6-27B- Intelligence
- 73%
- Task Time
- 6m 44s
- Intelligence / Joule
- 0.36
- Disk Size
- 55.6GB
- Power Draw
- 503W
Qwopus3.6 27B V2
Jackrong/Qwopus3.6-27B-v2
Quant —
Jackrong/Qwopus3.6-27B-v2- Intelligence
- 70%
- Task Time
- 10m 22s
- Intelligence / Joule
- 0.25
- Disk Size
- 55.6GB
- Power Draw
- 461W
ThinkingCap Qwen3.6 27B
bottlecapai/ThinkingCap-Qwen3.6-27B
Quant —
bottlecapai/ThinkingCap-Qwen3.6-27B- Intelligence
- 70%
- Task Time
- 4m 50s
- Intelligence / Joule
- 0.52
- Disk Size
- 55.6GB
- Power Draw
- 462W
Qwen3.6 27B
sakamakismile/Qwen3.6-27B-NVFP4
Quant nvfp4
sakamakismile/Qwen3.6-27B-NVFP4- Intelligence
- 64%
- Task Time
- 2m 29s
- Intelligence / Joule
- 1.04
- Disk Size
- 19.7GB
- Power Draw
- 416W
Qwen3.6 27Bunsloth/Qwen3.6-27B-NVFP4
Quant nvfp4
unsloth/Qwen3.6-27B-NVFP4- Intelligence
- 64%
- Task Time
- 3m 21s
- Intelligence / Joule
- 0.74
- Disk Size
- 23.4GB
- Power Draw
- 432W
Qwen3.6 27Bsakamakismile/Qwen3.6-27B-Text-NVFP4-MTP
Quant nvfp4
sakamakismile/Qwen3.6-27B-Text-NVFP4-MTP- Intelligence
- 57%
- Task Time
- 2m 14s
- Intelligence / Joule
- 1.33
- Disk Size
- 19.6GB
- Power Draw
- 318W
BTL 3
Quant —
Bbadtheorylabs/BTL-3- Intelligence
- 49%
- Task Time
- 3m 33s
- Intelligence / Joule
- 0.46
- Disk Size
- 0.9GB
- Power Draw
- 506W
Qwen3.6 35B A3B19
Qwen3.6 35B A3B
Quant —
Qwen/Qwen3.6-35B-A3B- Intelligence
- 70%
- Task Time
- 1m 39s
- Intelligence / Joule
- 1.86
- Disk Size
- 71.9GB
- Power Draw
- 382W
Qwen3.6 35B A3B
Quant nvfp4
nvidia/Qwen3.6-35B-A3B-NVFP4- Intelligence
- 70%
- Task Time
- 1m 15s
- Intelligence / Joule
- 3.49
- Disk Size
- 23.4GB
- Power Draw
- 265W
Qwen3.6 35B A3Bunsloth/Qwen3.6-35B-A3B-GGUF
Quant UD-Q4_K_M
unsloth/Qwen3.6-35B-A3B-GGUF- Intelligence
- 69%
- Task Time
- 1m 12s
- Intelligence / Joule
- 2.34
- Disk Size
- 22.1GB
- Power Draw
- 412W
Qwen3.6 35B A3Bunsloth/Qwen3.6-35B-A3B-GGUF
Quant UD-Q4_K_S
unsloth/Qwen3.6-35B-A3B-GGUF- Intelligence
- 69%
- Task Time
- 1m 11s
- Intelligence / Joule
- 2.74
- Disk Size
- 20.9GB
- Power Draw
- 353W
Qwen3.6 35B A3Bunsloth/Qwen3.6-35B-A3B-GGUF
Quant iq4xs
unsloth/Qwen3.6-35B-A3B-GGUF- Intelligence
- 68%
- Task Time
- 1m 28s
- Intelligence / Joule
- 2.31
- Disk Size
- 17.7GB
- Power Draw
- 337W
Qwen3.6 35B A3B
Quant fp8
Qwen/Qwen3.6-35B-A3B-FP8- Intelligence
- 68%
- Task Time
- 1m 23s
- Intelligence / Joule
- 2.98
- Disk Size
- 37.5GB
- Power Draw
- 273W
Qwen3.6 35B A3Bunsloth/Qwen3.6-35B-A3B-GGUF
Quant UD-Q3_K_S
unsloth/Qwen3.6-35B-A3B-GGUF- Intelligence
- 67%
- Task Time
- 1m 15s
- Intelligence / Joule
- 2.50
- Disk Size
- 15.4GB
- Power Draw
- 356W
Qwen3.6 35B A3Bunsloth/Qwen3.6-35B-A3B-GGUF
Quant MXFP4_MOE
unsloth/Qwen3.6-35B-A3B-GGUF- Intelligence
- 67%
- Task Time
- 1m 21s
- Intelligence / Joule
- 2.39
- Disk Size
- 21.7GB
- Power Draw
- 344W
Qwen3.6 35B A3Bunsloth/Qwen3.6-35B-A3B-GGUF
Quant q4kxl
unsloth/Qwen3.6-35B-A3B-GGUF- Intelligence
- 67%
- Task Time
- 1m 09s
- Intelligence / Joule
- 2.84
- Disk Size
- 22.4GB
- Power Draw
- 338W
Qwen3.6 35B A3Bunsloth/Qwen3.6-35B-A3B-GGUF
Quant q3km
unsloth/Qwen3.6-35B-A3B-GGUF- Intelligence
- 66%
- Task Time
- 1m 09s
- Intelligence / Joule
- 2.49
- Disk Size
- 16.6GB
- Power Draw
- 386W
Qwen3.6 35B A3Bunsloth/Qwen3.6-35B-A3B-GGUF
Quant UD-Q3_K_XL
unsloth/Qwen3.6-35B-A3B-GGUF- Intelligence
- 66%
- Task Time
- 1m 08s
- Intelligence / Joule
- 2.57
- Disk Size
- 16.8GB
- Power Draw
- 378W
Qwen3.6 35B A3Bunsloth/Qwen3.6-35B-A3B-GGUF
Quant iq3xxs
unsloth/Qwen3.6-35B-A3B-GGUF- Intelligence
- 66%
- Task Time
- 1m 35s
- Intelligence / Joule
- 1.78
- Disk Size
- 13.2GB
- Power Draw
- 389W
Qwen3.6 35B A3B
cyankiwi/Qwen3.6-35B-A3B-AWQ-4bit
Quant awq-4bit
cyankiwi/Qwen3.6-35B-A3B-AWQ-4bit- Intelligence
- 65%
- Task Time
- 1m 25s
- Intelligence / Joule
- 2.69
- Disk Size
- 25.0GB
- Power Draw
- 284W
Qwen3.6 35B A3Bunsloth/Qwen3.6-35B-A3B-GGUF
Quant UD-Q2_K_XL
unsloth/Qwen3.6-35B-A3B-GGUF- Intelligence
- 64%
- Task Time
- 1m 24s
- Intelligence / Joule
- 2.23
- Disk Size
- 12.3GB
- Power Draw
- 344W
Qwen3.6 35B A3Bunsloth/Qwen3.6-35B-A3B-GGUF
Quant UD-IQ3_S
unsloth/Qwen3.6-35B-A3B-GGUF- Intelligence
- 64%
- Task Time
- 1m 31s
- Intelligence / Joule
- 1.94
- Disk Size
- 13.7GB
- Power Draw
- 363W
Qwen3.6 35B A3Bunsloth/Qwen3.6-35B-A3B-GGUF
Quant UD-IQ2_M
unsloth/Qwen3.6-35B-A3B-GGUF- Intelligence
- 61%
- Task Time
- 1m 28s
- Intelligence / Joule
- 1.82
- Disk Size
- 11.5GB
- Power Draw
- 382W
Qwen3.6 35B A3Bunsloth/Qwen3.6-35B-A3B-GGUF
Quant iq2xxs
unsloth/Qwen3.6-35B-A3B-GGUF- Intelligence
- 61%
- Task Time
- 1m 27s
- Intelligence / Joule
- 2.01
- Disk Size
- 10.8GB
- Power Draw
- 348W
Qwen3.6 35B A3Bunsloth/Qwen3.6-35B-A3B-NVFP4
Quant nvfp4
unsloth/Qwen3.6-35B-A3B-NVFP4- Intelligence
- 59%
- Task Time
- 1m 14s
- Intelligence / Joule
- 2.52
- Disk Size
- 26.5GB
- Power Draw
- 319W
Qwen3.6 35B A3B Fastunsloth/Qwen3.6-35B-A3B-NVFP4-Fast
Quant nvfp4
unsloth/Qwen3.6-35B-A3B-NVFP4-Fast- Intelligence
- 59%
- Task Time
- 1m 15s
- Intelligence / Joule
- 2.50
- Disk Size
- 23.6GB
- Power Draw
- 312W
Ornith 1.0 35B3
Ornith 1.0 35Bdeepreinforce-ai/Ornith-1.0-35B-GGUF
Quant Q4_K_M
deepreinforce-ai/Ornith-1.0-35B-GGUF- Intelligence
- 67%
- Task Time
- 48s
- Intelligence / Joule
- 3.57
- Disk Size
- 21.2GB
- Power Draw
- 392W
Ornith 1.0 35Bdeepreinforce-ai/Ornith-1.0-35B-FP8
Quant fp8
deepreinforce-ai/Ornith-1.0-35B-FP8- Intelligence
- 66%
- Task Time
- 1m 07s
- Intelligence / Joule
- 2.60
- Disk Size
- 37.7GB
- Power Draw
- 377W
Ornith 1.0 35Bsakamakismile/Ornith-1.0-35B-NVFP4
Quant nvfp4
sakamakismile/Ornith-1.0-35B-NVFP4- Intelligence
- 53%
- Task Time
- 1m
- Intelligence / Joule
- 2.29
- Disk Size
- 21.9GB
- Power Draw
- 385W
Step 3.7 Flash3
Step 3.7 Flashunsloth/Step-3.7-Flash-GGUF
Quant UD-IQ2_XXS
unsloth/Step-3.7-Flash-GGUF- Intelligence
- 64%
- Task Time
- 1m 35s
- Intelligence / Joule
- 1.26
- Disk Size
- 61.7GB
- Power Draw
- 533W
Step 3.7 Flash
Quant IQ3_XXS
stepfun-ai/Step-3.7-Flash-GGUF- Intelligence
- 59%
- Task Time
- 1m 39s
- Intelligence / Joule
- 1.10
- Disk Size
- 75.8GB
- Power Draw
- 550W
Step 3.7 Flashunsloth/Step-3.7-Flash-GGUF
Quant UD-IQ2_M
unsloth/Step-3.7-Flash-GGUF- Intelligence
- 59%
- Task Time
- 1m 57s
- Intelligence / Joule
- 0.97
- Disk Size
- 61.8GB
- Power Draw
- 523W
Gemma 4 31B It4
Gemma 4 31B Itunsloth/gemma-4-31B-it-GGUF
Quant Q4_K_M
unsloth/gemma-4-31B-it-GGUF- Intelligence
- 59%
- Task Time
- 1m 41s
- Intelligence / Joule
- 1.15
- Disk Size
- 18.3GB
- Power Draw
- 514W
Gemma 4 31B It
google/gemma-4-31B-it
Quant —
google/gemma-4-31B-it- Intelligence
- 57%
- Task Time
- 1m 53s
- Intelligence / Joule
- 1.44
- Disk Size
- 62.5GB
- Power Draw
- 352W
Gemma 4 31B It
RedHatAI/gemma-4-31B-it-FP8-block
Quant fp8
RedHatAI/gemma-4-31B-it-FP8-block- Intelligence
- 57%
- Task Time
- 3m 04s
- Intelligence / Joule
- 0.96
- Disk Size
- 33.3GB
- Power Draw
- 323W
Gemma 4 31B Itcyankiwi/gemma-4-31B-it-AWQ-4bit
Quant awq-4bit
cyankiwi/gemma-4-31B-it-AWQ-4bit- Intelligence
- 54%
- Task Time
- 52s
- Intelligence / Joule
- 3.93
- Disk Size
- 20.9GB
- Power Draw
- 265W
Nemotron 3 Super 120B A12B2
NVIDIA Nemotron 3 Super 120B A12Bunsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF
Quant UD-Q3_K_M
unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF- Intelligence
- 58%
- Task Time
- 1m 33s
- Intelligence / Joule
- 1.20
- Disk Size
- 61.7GB
- Power Draw
- 523W
NVIDIA Nemotron 3 Super 120B A12B
Quant nvfp4
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4- Intelligence
- 56%
- Task Time
- 1m 46s
- Intelligence / Joule
- 1.19
- Disk Size
- 80.3GB
- Power Draw
- 446W
Agents A12
Agents A1InternScience/Agents-A1-Q4_K_M-GGUF
Quant q4km
InternScience/Agents-A1-Q4_K_M-GGUF- Intelligence
- 57%
- Task Time
- 56s
- Intelligence / Joule
- 3.14
- Disk Size
- 21.2GB
- Power Draw
- 326W
Agents A1InternScience/Agents-A1-FP8
Quant fp8
InternScience/Agents-A1-FP8- Intelligence
- 55%
- Task Time
- 1m 11s
- Intelligence / Joule
- 2.01
- Disk Size
- 37.7GB
- Power Draw
- 383W
Gpt Oss 120B1
Gpt Oss 120B
openai/gpt-oss-120b
Quant mxfp4
openai/gpt-oss-120b- Intelligence
- 56%
- Task Time
- 44s
- Intelligence / Joule
- 2.95
- Disk Size
- 65.2GB
- Power Draw
- 435W
Gemma 4 26B A4B3
Gemma 4 26B A4B ItRedHatAI/gemma-4-26B-A4B-it-FP8-dynamic
Quant fp8
RedHatAI/gemma-4-26B-A4B-it-FP8-dynamic- Intelligence
- 54%
- Task Time
- 1m 01s
- Intelligence / Joule
- 1.77
- Disk Size
- 28.6GB
- Power Draw
- 497W
Gemma 4 26B A4B Itcyankiwi/gemma-4-26B-A4B-it-AWQ-4bit
Quant awq-4bit
cyankiwi/gemma-4-26B-A4B-it-AWQ-4bit- Intelligence
- 53%
- Task Time
- 53s
- Intelligence / Joule
- 4.27
- Disk Size
- 17.2GB
- Power Draw
- 235W
Gemma 4 26B A4B
Quant nvfp4
nvidia/Gemma-4-26B-A4B-NVFP4- Intelligence
- 52%
- Task Time
- 48s
- Intelligence / Joule
- 4.25
- Disk Size
- 18.8GB
- Power Draw
- 255W
Bonsai 27B2
Ternary Bonsai 27B
Quant awq-4bit
prism-ml/Ternary-Bonsai-27B-AWQ-4bit- Intelligence
- 53%
- Task Time
- 5m 16s
- Intelligence / Joule
- 0.37
- Disk Size
- 18.7GB
- Power Draw
- 458W
Bonsai 27B
Quant awq-4bit
prism-ml/Bonsai-27B-AWQ-4bit- Intelligence
- 41%
- Task Time
- 6m 01s
- Intelligence / Joule
- 0.25
- Disk Size
- 18.7GB
- Power Draw
- 458W
Holo 3.1 35B A3B2
Holo 3.1 35B A3BHcompany/Holo-3.1-35B-A3B-NVFP4
Quant nvfp4
Hcompany/Holo-3.1-35B-A3B-NVFP4- Intelligence
- 53%
- Task Time
- 36s
- Intelligence / Joule
- 4.53
- Disk Size
- 23.7GB
- Power Draw
- 321W
Holo 3.1 35B A3BHcompany/Holo-3.1-35B-A3B-GGUF
Quant q4_k_m
Hcompany/Holo-3.1-35B-A3B-GGUF- Intelligence
- 52%
- Task Time
- 39s
- Intelligence / Joule
- 3.33
- Disk Size
- 21.3GB
- Power Draw
- 400W
Gemma 4 12B It3
Gemma 4 12B Itunsloth/gemma-4-12b-it-GGUF
Quant q4km
unsloth/gemma-4-12b-it-GGUF- Intelligence
- 52%
- Task Time
- 1m 16s
- Intelligence / Joule
- 1.79
- Disk Size
- 7.1GB
- Power Draw
- 379W
Gemma 4 12B Itgoogle/gemma-4-12B-it
Quant —
google/gemma-4-12B-it- Intelligence
- 45%
- Task Time
- 1m 44s
- Intelligence / Joule
- 1.53
- Disk Size
- 23.9GB
- Power Draw
- 285W
Gemma 4 12B It Qat W4a16 Ctgoogle/gemma-4-12B-it-qat-w4a16-ct
Quant —
google/gemma-4-12B-it-qat-w4a16-ct- Intelligence
- 42%
- Task Time
- 1m 36s
- Intelligence / Joule
- 1.40
- Disk Size
- 10.3GB
- Power Draw
- 316W
Laguna XS 2.11
Laguna XS 2.1poolside/Laguna-XS-2.1-GGUF
Quant Q4_K_M
poolside/Laguna-XS-2.1-GGUF- Intelligence
- 52%
- Task Time
- 2m 45s
- Intelligence / Joule
- 0.68
- Disk Size
- 20.3GB
- Power Draw
- 464W
Qwen3.5 9B Base3
Qwen3.5 9Bunsloth/Qwen3.5-9B-GGUF
Quant Q4_K_M
unsloth/Qwen3.5-9B-GGUF- Intelligence
- 51%
- Task Time
- 1m 17s
- Intelligence / Joule
- 1.18
- Disk Size
- 5.7GB
- Power Draw
- 562W
Qwen3.5 9B
Quant —
Qwen/Qwen3.5-9B- Intelligence
- 30%
- Task Time
- 2m 32s
- Intelligence / Joule
- 0.62
- Disk Size
- 19.3GB
- Power Draw
- 322W
Qwen3.5 9Bcyankiwi/Qwen3.5-9B-AWQ-4bit
Quant awq-4bit
cyankiwi/Qwen3.5-9B-AWQ-4bit- Intelligence
- 27%
- Task Time
- 1m 39s
- Intelligence / Joule
- 0.55
- Disk Size
- 9.1GB
- Power Draw
- 486W
Qwen3.5 9B1
Qwen3.5 9B
lovedheart/Qwen3.5-9B-FP8
Quant fp8
lovedheart/Qwen3.5-9B-FP8- Intelligence
- 46%
- Task Time
- 1m 50s
- Intelligence / Joule
- 0.82
- Disk Size
- 12.2GB
- Power Draw
- 513W
Gpt Oss 20B1
Gpt Oss 20Bopenai/gpt-oss-20b
Quant mxfp4
openai/gpt-oss-20b- Intelligence
- 42%
- Task Time
- 43s
- Intelligence / Joule
- 2.81
- Disk Size
- 13.8GB
- Power Draw
- 352W
Nemotron 3 Nano 30B A3B2
NVIDIA Nemotron 3 Nano 30B A3B
Quant fp8
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8- Intelligence
- 38%
- Task Time
- 44s
- Intelligence / Joule
- 2.65
- Disk Size
- 32.7GB
- Power Draw
- 329W
NVIDIA Nemotron 3 Nano 30B A3B
Quant nvfp4
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4- Intelligence
- 38%
- Task Time
- 33s
- Intelligence / Joule
- 3.06
- Disk Size
- 19.3GB
- Power Draw
- 373W
Nemotron 3 Nano Omni 30B A3B Reasoning1
Nemotron 3 Nano Omni 30B A3B Reasoning
Quant nvfp4
nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4- Intelligence
- 33%
- Task Time
- 35s
- Intelligence / Joule
- 4.08
- Disk Size
- 22.4GB
- Power Draw
- 230W
Gemma 4 E4B It3
Gemma 4 E4B Itunsloth/gemma-4-E4B-it-GGUF
Quant Q4_K_M
unsloth/gemma-4-E4B-it-GGUF- Intelligence
- 29%
- Task Time
- 15s
- Intelligence / Joule
- 4.74
- Disk Size
- 5.0GB
- Power Draw
- 407W
Gemma 4 E4B It
Quant fp8
PprithivMLmods/gemma-4-E4B-it-FP8- Intelligence
- 27%
- Task Time
- 19s
- Intelligence / Joule
- 3.63
- Disk Size
- 13.3GB
- Power Draw
- 390W
Gemma 4 E4B It
leon-se/gemma-4-E4B-it-FP8-Dynamic
Quant fp8
leon-se/gemma-4-E4B-it-FP8-Dynamic- Intelligence
- 25%
- Task Time
- 12s
- Intelligence / Joule
- 9.40
- Disk Size
- 13.3GB
- Power Draw
- 219W
Gemma 4 E2B It3
Gemma 4 E2B Itunsloth/gemma-4-E2B-it-GGUF
Quant UD-Q8_K_XL
unsloth/gemma-4-E2B-it-GGUF- Intelligence
- 21%
- Task Time
- 12s
- Intelligence / Joule
- 5.01
- Disk Size
- 5.3GB
- Power Draw
- 350W
Gemma 4 E2B Itleon-se/gemma-4-E2B-it-FP8-Dynamic
Quant fp8
leon-se/gemma-4-E2B-it-FP8-Dynamic- Intelligence
- 18%
- Task Time
- 8s
- Intelligence / Joule
- 10.43
- Disk Size
- 9.2GB
- Power Draw
- 202W
Gemma 4 E2B Itunsloth/gemma-4-E2B-it-GGUF
Quant UD-Q4_K_XL
unsloth/gemma-4-E2B-it-GGUF- Intelligence
- 18%
- Task Time
- 9s
- Intelligence / Joule
- 6.18
- Disk Size
- 3.2GB
- Power Draw
- 310W
LFM2.5 8B A1B2
LFM2.5 8B A1B
Quant Q8_0
LiquidAI/LFM2.5-8B-A1B-GGUF- Intelligence
- 13%
- Task Time
- 6s
- Intelligence / Joule
- 7.07
- Disk Size
- 9.0GB
- Power Draw
- 336W
LFM2.5 8B A1B
Quant —
LiquidAI/LFM2.5-8B-A1B- Intelligence
- 10%
- Task Time
- 5s
- Intelligence / Joule
- 4.05
- Disk Size
- 16.9GB
- Power Draw
- 460W
Qwen 3.8 27B3 variations—81%0.804m 51s31GB346W
Qwen3.6 27B9 variations—74%1.602m 14s0.9GB318W
Qwen3.6 35B A3B19 variations—70%3.491m 08s11GB265W
Ornith 1.0 35B3 variations—67%3.5748s21GB377W
Step 3.7 Flash3 variations—64%1.261m 35s62GB523W
Gemma 4 31B It4 variations—59%3.9352s18GB265W
Nemotron 3 Super 120B A12B2 variations—58%1.201m 33s62GB446W
NVIDIA Nemotron 3 Super 120B A12Bunsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUFUD-Q3_K_M58%1.201m 33s62GB523W
unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUFUD-Q3_K_M58%1.201m 33s62GB523WNVIDIA Nemotron 3 Super 120B A12Bnvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4nvfp456%1.191m 46s80GB446W
Agents A12 variations—57%3.1456s21GB326W
Gpt Oss 120B1 variationmxfp456%2.9544s65GB435W
Gemma 4 26B A4B3 variations—54%4.2748s17GB235W
Bonsai 27B2 variations—53%0.375m 16s19GB458W
Holo 3.1 35B A3B2 variations—53%4.5336s21GB321W
Gemma 4 12B It3 variations—52%1.791m 16s7.1GB285W
Laguna XS 2.11 variationQ4_K_M52%0.682m 45s20GB464W
Qwen3.5 9B Base3 variations—51%1.181m 17s5.7GB322W
Qwen3.5 9B1 variationfp846%0.821m 50s12GB513W
Gpt Oss 20B1 variationmxfp442%2.8143s14GB352W
Nemotron 3 Nano 30B A3B2 variations—38%3.0633s19GB329W
Nemotron 3 Nano Omni 30B A3B Reasoning1 variationnvfp433%4.0835s22GB230W
Nemotron 3 Nano Omni 30B A3B Reasoningnvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4nvfp433%4.0835s22GB230W