Hugging Face's logo

Inference Providers

·

Metrics for top trending models

Browse all models Learn more
Kimi-K2-Thinking
novita
cheapest
0.6 2.5 262144 1.47 11 Yes No
Kimi-K2-Thinking
together
fastest
1.2 4 262144 0.73 37 Yes Yes
DeepSeek-OCR
novita
0.03 0.03 8192 0.73 189 No No
MiniMax-M2
novita
0.3 1.2 204800 1.06 59 No No
Llama-3.1-8B-Instruct
novita
cheapest
0.02 0.05 16384 0.78 82 No No
Llama-3.1-8B-Instruct
nebius
0.03 0.09 131072 0.48 179 No Yes
Llama-3.1-8B-Instruct
cerebras
fastest
0.1 0.1 - 0.41 1105 No No
Llama-3.1-8B-Instruct
sambanova
0.1 0.2 16384 0.87 512 Yes Yes
Llama-3.1-8B-Instruct
nscale
0.06 0.06 131072 1.05 58 No No
Llama-3.1-8B-Instruct
fireworks-ai
0.2 0.2 131072 0.39 228 No No
Llama-3.1-8B-Instruct
scaleway
- - - 0.60 97 Yes Yes
GLM-4.6
novita
cheapest
0.6 2.2 204800 1.32 24 Yes No
GLM-4.6
cerebras
fastest
- - - 0.39 414 Yes No
GLM-4.6
zai-org
- - - 2.64 24 Yes No
gpt-oss-20b
groq
fastest
0.1 0.5 131072 0.19 807 Yes No
gpt-oss-20b
novita
0.04 0.15 131072 1.04 105 No Yes
gpt-oss-20b
nebius
0.05 0.2 131072 0.40 159 Yes Yes
gpt-oss-20b
nscale
0.05 0.2 131072 1.05 60 Yes Yes
gpt-oss-20b
hyperbolic
cheapest
0.1 0.1 131072 1.30 85 No No
gpt-oss-20b
together
0.05 0.2 131072 0.30 189 Yes No
gpt-oss-20b
fireworks-ai
0.05 0.2 131072 0.94 160 Yes No
gpt-oss-120b
groq
0.15 0.75 131072 0.29 416 Yes No
gpt-oss-120b
novita
cheapest
0.05 0.25 131072 1.00 108 No Yes
gpt-oss-120b
nebius
0.15 0.6 131072 0.49 68 Yes Yes
gpt-oss-120b
cerebras
fastest
0.25 0.69 - 0.36 609 Yes No
gpt-oss-120b
sambanova
0.22 0.59 131072 0.93 404 Yes Yes
gpt-oss-120b
nscale
0.1 0.4 131072 1.08 88 Yes Yes
gpt-oss-120b
hyperbolic
0.3 0.3 131072 0.82 264 Yes No
gpt-oss-120b
together
0.15 0.6 131072 0.32 208 Yes Yes
gpt-oss-120b
fireworks-ai
0.15 0.6 131072 0.78 113 Yes No
gpt-oss-120b
scaleway
- - - 0.46 139 Yes Yes
DeepSeek-V3.2-Exp
novita
0.27 0.41 163840 0.97 28 Yes Yes
DeepSeek-R1
novita
0.7 2.5 64000 0.78 23 Yes No
DeepSeek-R1
sambanova
fastest
- - - 1.93 114 Yes No
DeepSeek-R1
hyperbolic
cheapest
2 2 163840 1.04 33 No No
DeepSeek-R1
together
3 7 163840 1.25 25 No Yes
DeepSeek-R1
fireworks-ai
- - - - - - -
Qwen3-4B-Instruct-2507
nscale
0.01 0.03 262144 0.90 69 Yes No
Kimi-K2-Instruct-0905
groq
fastest
- - 262144 0.49 173 Yes No
Kimi-K2-Instruct-0905
novita
cheapest
0.6 2.5 262144 0.90 45 Yes No
Kimi-K2-Instruct-0905
together
1 3 262144 0.59 51 Yes Yes
Qwen3-VL-8B-Instruct
novita
0.08 0.5 131072 0.82 65 Yes Yes
Qwen3-8B
nscale
0.07 0.18 40960 0.88 56 Yes No
Qwen2.5-7B-Instruct
together
0.3 0.3 32768 0.40 139 Yes Yes
Llama-3.2-3B-Instruct
novita
cheapest
0.03 0.05 32768 0.60 129 Yes No
Llama-3.2-3B-Instruct
sambanova
- - - - - - -
Llama-3.2-3B-Instruct
hyperbolic
0.1 0.1 131072 0.88 114 No No
Llama-3.2-3B-Instruct
together
fastest
0.06 0.06 131072 0.85 137 Yes Yes
Qwen3-Coder-30B-A3B-Instruct
nebius
cheapest
0.1 0.3 262144 0.45 53 Yes Yes
Qwen3-Coder-30B-A3B-Instruct
fireworks-ai
- - - - - - -
Qwen3-Coder-30B-A3B-Instruct
scaleway
fastest
- - - 0.44 95 Yes No
Qwen3-VL-30B-A3B-Instruct
novita
0.2 0.7 131072 0.63 109 Yes Yes
Meta-Llama-3-8B-Instruct
groq
- - - - - - -
Meta-Llama-3-8B-Instruct
novita
0.04 0.04 8192 0.75 75 No No
Meta-Llama-3-8B-Instruct
together
- - - - - - -
Qwen2.5-VL-7B-Instruct
hyperbolic
0.2 0.2 32768 0.61 84 No No
Kimi-K2-Instruct
novita
cheapest
0.57 2.3 131072 1.16 32 Yes Yes
Kimi-K2-Instruct
nebius
0.5 2.4 131072 0.53 38 Yes Yes
Kimi-K2-Instruct
together
fastest
1 3 131072 0.73 47 Yes Yes
Kimi-K2-Instruct
fireworks-ai
0.6 2.5 131072 1.11 45 Yes No
Llama-3.2-1B-Instruct
novita
- - 131000 0.87 201 No No
Llama-3.2-1B-Instruct
sambanova
- - - - - - -
DeepSeek-R1-Distill-Qwen-1.5B
nscale
0.1 0.1 131072 0.96 132 No No
Qwen3-Next-80B-A3B-Instruct
novita
0.15 1.5 131072 0.98 130 Yes No
Qwen3-Next-80B-A3B-Instruct
hyperbolic
cheapest fastest
0.3 0.3 262144 0.72 158 Yes No
Qwen3-Next-80B-A3B-Instruct
together
0.15 1.5 262144 0.68 150 Yes Yes
gemma-3-27b-it
nebius
cheapest fastest
0.2 0.6 110000 0.38 76 No Yes
gemma-3-27b-it
scaleway
- - - 0.57 43 Yes No
Llama-3.3-70B-Instruct
groq
0.59 0.79 131072 0.31 287 Yes No
Llama-3.3-70B-Instruct
novita
cheapest
0.13 0.39 131072 1.20 26 No No
Llama-3.3-70B-Instruct
nebius
0.25 0.75 131072 0.55 127 Yes Yes
Llama-3.3-70B-Instruct
cerebras
fastest
0.85 1.2 - 0.32 1025 Yes No
Llama-3.3-70B-Instruct
sambanova
0.6 1.2 131072 0.58 302 Yes Yes
Llama-3.3-70B-Instruct
nscale
0.4 0.4 131072 1.20 16 No Yes
Llama-3.3-70B-Instruct
hyperbolic
0.4 0.4 131072 0.71 135 No No
Llama-3.3-70B-Instruct
together
0.88 0.88 131072 0.37 113 Yes Yes
Llama-3.3-70B-Instruct
fireworks-ai
0.9 0.9 131072 0.52 132 No No
Llama-3.3-70B-Instruct
scaleway
- - - 0.70 37 Yes Yes
GLM-4.5-Air
novita
cheapest
0.13 0.85 131072 0.76 59 Yes No
GLM-4.5-Air
nebius
fastest
0.2 1.2 131072 0.44 68 Yes Yes
GLM-4.5-Air
fireworks-ai
- - - - - - -
GLM-4.5-Air
zai-org
- - - 3.10 50 Yes No
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
0.09 0.58 131072 0.98 28 Yes Yes
Qwen3-235B-A22B-Instruct-2507
nebius
0.2 0.6 262144 0.55 55 Yes Yes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
0.6 1.2 - 1.05 402 Yes No
Qwen3-235B-A22B-Instruct-2507
nscale
0.2 0.6 32768 1.10 24 Yes Yes
Qwen3-235B-A22B-Instruct-2507
hyperbolic
2 2 262144 1.70 60 Yes No
Qwen3-235B-A22B-Instruct-2507
together
0.2 0.6 262144 0.50 31 Yes Yes
Qwen3-235B-A22B-Instruct-2507
fireworks-ai
0.22 0.88 262144 0.97 51 Yes No
Qwen3-235B-A22B-Instruct-2507
scaleway
- - - 0.54 69 Yes Yes
Qwen3-VL-235B-A22B-Thinking
novita
0.98 3.95 131072 1.71 32 No No
gpt-oss-safeguard-20b
groq
- - 131072 0.23 791 Yes No
SmolLM3-3B
hf-inference
- - - 0.22 86 Yes Yes
Qwen3-14B
nscale
0.07 0.2 40960 1.06 47 Yes Yes
DeepSeek-R1-0528-Qwen3-8B
novita
0.06 0.09 128000 0.86 52 No No
Qwen3-32B
groq
0.29 0.59 131072 0.30 263 Yes No
Qwen3-32B
novita
0.1 0.45 40960 0.85 23 No No
Qwen3-32B
nebius
0.1 0.3 40960 0.60 43 Yes Yes
Qwen3-32B
cerebras
fastest
0.4 0.8 - 0.38 947 No No
Qwen3-32B
sambanova
0.4 0.8 32768 2.96 172 Yes Yes
Qwen3-32B
nscale
cheapest
0.08 0.25 40960 1.51 26 Yes No
Llama-4-Maverick-17B-128E-Instruct
groq
cheapest fastest
0.2 0.6 131072 0.94 312 Yes No
Llama-4-Maverick-17B-128E-Instruct
sambanova
0.63 1.8 131072 2.64 238 Yes Yes
Llama-4-Maverick-17B-128E-Instruct
fireworks-ai
0.22 0.88 1048576 0.64 75 Yes No
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
0.29 1.2 262144 1.00 35 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
nebius
0.4 1.8 262144 2.18 28 No Yes
Qwen3-Coder-480B-A35B-Instruct
cerebras
- - - - - - -
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
2 2 262144 1.22 32 Yes No
Qwen3-Coder-480B-A35B-Instruct
together
fastest
2 2 262144 0.55 54 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
fireworks-ai
0.45 1.8 262144 1.73 21 No No
DeepSeek-V3-0324
novita
0.27 1.12 163840 1.22 31 Yes Yes
DeepSeek-V3-0324
nebius
0.75 2.25 32768 1.68 85 No No
DeepSeek-V3-0324
sambanova
fastest
3 4.5 131072 0.75 167 Yes Yes
DeepSeek-V3-0324
hyperbolic
1.25 1.25 163840 1.02 34 No No
DeepSeek-V3-0324
together
1.25 1.25 131072 0.64 50 Yes Yes
DeepSeek-V3-0324
fireworks-ai
cheapest
0.9 0.9 163840 1.40 53 Yes No
Llama-4-Scout-17B-16E-Instruct
groq
fastest
0.11 0.34 131072 0.25 356 Yes No
Llama-4-Scout-17B-16E-Instruct
novita
0.1 0.5 131072 0.48 40 No No
Llama-4-Scout-17B-16E-Instruct
sambanova
- - - - - - -
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
0.09 0.29 890000 0.85 33 Yes Yes
Llama-4-Scout-17B-16E-Instruct
together
0.18 0.59 1048576 0.97 63 Yes Yes
Llama-4-Scout-17B-16E-Instruct
fireworks-ai
0.15 0.6 1048576 0.68 69 Yes No
gemma-2-2b-it
nebius
0.02 0.06 8192 0.40 146 No Yes
GLM-4.5
novita
0.6 2.2 131072 0.73 43 Yes No
GLM-4.5
nebius
0.6 2.2 131072 0.44 37 Yes Yes
GLM-4.5
fireworks-ai
cheapest fastest
0.55 2.19 131072 1.04 67 Yes No
GLM-4.5
zai-org
- - - 2.86 56 Yes No
DeepSeek-R1-Distill-Qwen-7B
nscale
0.15 0.15 131072 0.94 66 No No
DeepSeek-R1-Distill-Qwen-14B
novita
cheapest fastest
0.15 0.15 32768 0.97 54 No No
DeepSeek-R1-Distill-Qwen-14B
nscale
0.2 0.2 131072 0.95 37 No No
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
0.06 0.2 131072 1.05 27 No Yes
Qwen2.5-Coder-32B-Instruct
hyperbolic
fastest
0.2 0.2 32768 1.07 74 No No
Qwen2.5-Coder-32B-Instruct
together
- - - - - - -
Qwen2.5-Coder-32B-Instruct
scaleway
- - - 0.57 39 Yes No
Apertus-8B-Instruct-2509
publicai
- - - 1.00 88 No Yes
Qwen3-30B-A3B-Instruct-2507
nebius
0.1 0.3 262144 0.42 49 Yes Yes
Qwen3-VL-30B-A3B-Thinking
novita
0.2 1 131072 0.80 84 Yes Yes
DeepSeek-V3.1
novita
cheapest
0.27 1 131072 1.25 29 Yes No
DeepSeek-V3.1
together
0.6 1.7 131072 1.27 60 Yes No
DeepSeek-V3.1
fireworks-ai
fastest
- - 163840 0.78 90 Yes No
DeepSeek-V3
novita
0.4 1.3 64000 1.44 28 Yes No
DeepSeek-V3
together
cheapest fastest
1.25 1.25 131072 0.62 47 Yes Yes
DeepSeek-V3
fireworks-ai
- - - - - - -
Qwen2.5-Coder-7B-Instruct
nscale
0.01 0.03 131072 1.04 60 No Yes
Qwen3-235B-A22B
novita
0.2 0.8 40960 1.02 36 No No
Qwen3-235B-A22B
nscale
cheapest
0.2 0.6 32000 1.05 23 Yes Yes
Qwen3-235B-A22B
together
0.2 0.6 40960 0.56 47 Yes Yes
Qwen3-235B-A22B
fireworks-ai
fastest
0.22 0.88 131072 0.96 76 Yes No
Qwen3-30B-A3B
novita
cheapest
0.09 0.45 40960 0.77 106 No No
Qwen3-30B-A3B
fireworks-ai
fastest
0.15 0.6 131072 0.86 135 Yes No
GLM-4.5V
novita
cheapest
0.6 1.8 65536 1.82 56 Yes No
GLM-4.5V
zai-org
fastest
- - - 2.73 57 Yes No
Llama-3.1-70B-Instruct
fireworks-ai
0.9 0.9 131072 0.52 133 No No
GLM-4.6-FP8
zai-org
- - - 3.36 43 Yes No
Qwen3-VL-235B-A22B-Instruct
novita
0.3 1.5 131072 0.94 26 Yes Yes
Qwen3-Next-80B-A3B-Thinking
novita
0.15 1.5 131072 0.91 120 Yes No
Qwen3-Next-80B-A3B-Thinking
hyperbolic
cheapest fastest
0.3 0.3 262144 0.76 169 Yes No
Qwen3-Next-80B-A3B-Thinking
together
- - - - - - -
NVIDIA-Nemotron-Nano-12B-v2
nebius
0.07 0.2 131072 0.56 121 No Yes
gemma-2-9b-it
groq
- - - - - - -
gemma-2-9b-it
nebius
0.03 0.09 8192 0.37 128 No Yes
ERNIE-4.5-VL-424B-A47B-Base-PT
novita
0.42 1.25 123000 1.31 41 No No
Qwen3-4B-Thinking-2507
nscale
0.01 0.03 262144 0.98 84 Yes No
DeepSeek-R1-Distill-Llama-70B
groq
- - - - - - -
DeepSeek-R1-Distill-Llama-70B
novita
0.8 0.8 8192 1.65 31 No No
DeepSeek-R1-Distill-Llama-70B
sambanova
fastest
0.7 1.4 131072 0.87 189 No No
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
0.75 0.75 131072 0.94 16 No Yes
DeepSeek-R1-Distill-Llama-70B
scaleway
- - - 0.64 25 No Yes
Llama-4-Maverick-17B-128E-Instruct-FP8
novita
cheapest
0.17 0.85 1048576 0.41 54 No No
Llama-4-Maverick-17B-128E-Instruct-FP8
together
fastest
0.27 0.85 1048576 0.43 77 Yes Yes
DeepSeek-R1-Distill-Llama-8B
novita
- - - - - - -
DeepSeek-R1-Distill-Llama-8B
nscale
0.05 0.05 131072 0.96 56 No Yes
Qwen2.5-72B-Instruct
novita
cheapest
0.38 0.4 32000 1.20 19 Yes No
Qwen2.5-72B-Instruct
hyperbolic
0.4 0.4 131072 1.00 37 Yes No
Qwen2.5-72B-Instruct
together
fastest
1.2 1.2 131072 0.60 78 Yes Yes
Qwen2.5-72B-Instruct
fireworks-ai
- - - - - - -
GLM-4.5V-FP8
zai-org
- - - 2.79 53 Yes No
ERNIE-4.5-VL-28B-A3B-PT
novita
0.14 0.56 30000 1.00 79 No No
Arch-Router-1.5B
hf-inference
- - - 0.22 54 No Yes
aya-expanse-32b
cohere
- - - 0.32 40 No No
Llama-Guard-4-12B
groq
0.2 0.2 131072 0.31 6 No No
Qwen2.5-VL-72B-Instruct
nebius
0.25 0.75 32000 0.44 32 No Yes
Qwen2.5-VL-72B-Instruct
hyperbolic
cheapest fastest
0.6 0.6 32768 1.34 35 No No
ERNIE-4.5-0.3B-PT
novita
- - 120000 0.96 104 No No
Qwen3-30B-A3B-Thinking-2507
nebius
0.1 0.3 262144 0.48 102 Yes Yes
Baichuan-M2-32B
novita
0.07 0.07 131072 2.03 41 No Yes
DeepSeek-V3.1-Terminus
novita
0.27 1 131072 1.35 30 No Yes
c4ai-command-a-03-2025
cohere
- - - 0.36 43 Yes No
Qwen3-Coder-480B-A35B-Instruct-FP8
together
2 2 262144 0.65 54 Yes Yes
Meta-Llama-3-70B-Instruct
groq
- - - - - - -
Meta-Llama-3-70B-Instruct
novita
0.51 0.74 8192 0.75 28 No Yes
Meta-Llama-3-70B-Instruct
hyperbolic
cheapest
0.4 0.4 8192 0.78 87 No No
Meta-Llama-3-70B-Instruct
together
fastest
0.88 0.88 8192 0.34 97 No Yes
QwQ-32B
groq
- - - - - - -
QwQ-32B
nebius
- - - - - - -
QwQ-32B
sambanova
- - - - - - -
QwQ-32B
nscale
cheapest
0.18 0.2 131072 0.94 26 Yes Yes
QwQ-32B
hyperbolic
fastest
0.4 0.4 131072 1.03 59 No No
QwQ-32B
fireworks-ai
- - - - - - -
DeepSeek-R1-0528
novita
0.7 2.5 163840 0.88 25 Yes No
DeepSeek-R1-0528
nebius
cheapest
0.8 2.4 163840 0.58 24 No Yes
DeepSeek-R1-0528
sambanova
fastest
5 7 131072 1.10 133 Yes Yes
DeepSeek-R1-0528
hyperbolic
3 3 163840 1.66 37 No No
DeepSeek-R1-0528
together
3 7 163840 0.68 30 No Yes
DeepSeek-R1-0528
fireworks-ai
3 8 163840 1.31 47 Yes No
Qwen3-235B-A22B-Thinking-2507
novita
0.3 3 131072 0.94 32 Yes No
Qwen3-235B-A22B-Thinking-2507
cerebras
- - - - - - -
Qwen3-235B-A22B-Thinking-2507
fireworks-ai
cheapest fastest
0.22 0.88 262144 0.67 42 Yes No
Qwen2.5-VL-32B-Instruct
fireworks-ai
0.22 0.88 128000 1.48 38 No No
Llama-3.1-405B-Instruct
sambanova
- - - - - - -
Llama-3.1-405B-Instruct
fireworks-ai
3 3 131072 0.67 65 Yes No
command-a-translate-08-2025
cohere
- - - 0.54 63 Yes No
GLM-4.1V-9B-Thinking
novita
0.035 0.138 65536 0.74 70 No No
ERNIE-4.5-21B-A3B-PT
novita
0.07 0.28 120000 0.74 82 No No
DeepSeek-R1-Distill-Qwen-32B
novita
cheapest
0.3 0.3 64000 0.82 22 No Yes
DeepSeek-R1-Distill-Qwen-32B
nscale
fastest
0.3 0.3 131072 1.03 25 No No
MiniMax-M1-80k
novita
0.55 2.2 1000000 1.70 57 Yes No
GLM-4-32B-0414
novita
0.55 1.66 32000 1.03 37 No No
Hermes-2-Pro-Llama-3-8B
novita
0.14 0.14 8192 0.58 104 No No
c4ai-command-r7b-arabic-02-2025
cohere
- - - 0.38 78 No No
AFM-4.5B
together
0.048 0.15 65536 0.57 199 No Yes
L3-8B-Stheno-v3.2
novita
0.05 0.05 8192 0.72 71 No No
c4ai-command-r-08-2024
cohere
- - - 0.29 57 Yes No
Mixtral-8x22B-Instruct-v0.1
nscale
cheapest
1.2 1.2 65536 1.06 22 No Yes
Mixtral-8x22B-Instruct-v0.1
together
- - - - - - -
Mixtral-8x22B-Instruct-v0.1
fireworks-ai
fastest
1.2 1.2 65536 0.45 69 No No
command-a-reasoning-08-2025
cohere
- - - 0.27 91 Yes No
c4ai-command-r7b-12-2024
cohere
- - - 0.41 105 Yes No
cogito-v2-preview-deepseek-671B-MoE
together
1.25 1.25 163840 0.33 47 No Yes
cogito-v2-preview-llama-405B
together
3.5 3.5 32768 1.24 26 Yes Yes
cogito-v2-preview-llama-109B-MoE
together
0.18 0.59 32767 0.65 84 Yes Yes
aya-vision-32b
cohere
- - - 0.41 56 No No
GLM-4.5-Air-FP8
together
0.2 1.1 131072 0.61 103 Yes Yes
command-a-vision-07-2025
cohere
- - - 0.37 63 No No
cogito-v2-preview-llama-70B
together
0.88 0.88 32768 1.04 51 Yes Yes
Hermes-4-405B
nebius
1 3 131072 0.38 33 No No
Qwen2.5-Coder-3B-Instruct
nscale
0.01 0.03 32768 0.95 72 No Yes
ERNIE-4.5-300B-A47B-Base-PT
novita
0.28 1.1 123000 0.97 25 No Yes
DeepSeek-Prover-V2-671B
novita
0.7 2.5 160000 0.60 32 No No
L3-8B-Lunaris-v1
novita
0.05 0.05 8192 0.81 67 No No
Apertus-70B-Instruct-2509
publicai
- - - 1.19 51 No Yes
Gemma-SEA-LION-v4-27B-IT
publicai
- - - 1.43 49 No Yes
WizardLM-2-8x22B
novita
0.62 0.62 65535 0.48 47 No No
Hermes-4-70B
nebius
0.13 0.4 131072 0.65 87 No No
Llama-3.3-Swallow-70B-Instruct-v0.4
sambanova
0.6 1.2 131072 2.09 166 No Yes
marin-8b-instruct
together
0.18 0.18 4096 0.29 145 No Yes
Llama-3_1-Nemotron-Ultra-253B-v1
nebius
0.6 1.8 131072 0.50 39 No Yes
Qwen2.5-Coder-7B
nebius
0.03 0.09 32768 0.37 194 No Yes
Hermes-3-Llama-3.1-70B
hyperbolic
0.4 0.4 12288 0.47 30 No No
Dobby-Unhinged-Llama-3.3-70B
fireworks-ai
0.9 0.9 131072 0.43 49 No No
Qwen3-235B-A22B-FP8
together
0.2 0.6 40960 0.66 46 Yes Yes