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 0.85 34 Yes No
Kimi-K2-Thinking
together
fastest
1.2 4 262144 0.42 80 Yes Yes
DeepSeek-OCR
novita
0.03 0.03 8192 0.69 169 No No
MiniMax-M2
novita
0.3 1.2 204800 1.24 67 No No
Llama-3.1-8B-Instruct
novita
cheapest
0.02 0.05 16384 0.78 65 No No
Llama-3.1-8B-Instruct
nebius
0.03 0.09 131072 0.40 175 No No
Llama-3.1-8B-Instruct
cerebras
fastest
0.1 0.1 - 0.32 1247 No No
Llama-3.1-8B-Instruct
sambanova
0.1 0.2 16384 0.89 496 Yes Yes
Llama-3.1-8B-Instruct
nscale
0.06 0.06 131072 0.89 59 No Yes
Llama-3.1-8B-Instruct
fireworks-ai
0.2 0.2 131072 0.38 235 No No
Llama-3.1-8B-Instruct
scaleway
- - - 0.49 112 Yes Yes
GLM-4.6
novita
cheapest
0.6 2.2 204800 0.80 46 Yes No
GLM-4.6
cerebras
fastest
- - - 0.31 404 Yes No
GLM-4.6
zai-org
- - - 3.42 57 Yes No
gpt-oss-20b
groq
fastest
0.1 0.5 131072 0.22 747 Yes No
gpt-oss-20b
novita
0.04 0.15 131072 0.71 199 No Yes
gpt-oss-20b
nebius
0.05 0.2 131072 0.36 146 Yes Yes
gpt-oss-20b
nscale
0.05 0.2 131072 1.03 8 Yes Yes
gpt-oss-20b
hyperbolic
cheapest
0.1 0.1 131072 0.74 154 No No
gpt-oss-20b
together
0.05 0.2 131072 0.36 171 Yes Yes
gpt-oss-20b
fireworks-ai
0.05 0.2 131072 0.66 204 Yes No
gpt-oss-120b
groq
0.15 0.75 131072 0.21 414 Yes No
gpt-oss-120b
novita
cheapest
0.05 0.25 131072 0.77 176 No Yes
gpt-oss-120b
nebius
0.15 0.6 131072 0.42 91 Yes Yes
gpt-oss-120b
cerebras
fastest
0.25 0.69 - 0.34 914 Yes No
gpt-oss-120b
sambanova
0.22 0.59 131072 0.98 395 Yes Yes
gpt-oss-120b
nscale
0.1 0.4 131072 1.05 91 Yes Yes
gpt-oss-120b
hyperbolic
0.3 0.3 131072 1.44 244 Yes No
gpt-oss-120b
together
0.15 0.6 131072 0.37 157 Yes No
gpt-oss-120b
fireworks-ai
- - - - - - -
gpt-oss-120b
scaleway
- - - 0.54 141 Yes Yes
Kimi-K2-Instruct-0905
groq
fastest
- - 262144 0.26 165 Yes No
Kimi-K2-Instruct-0905
novita
cheapest
0.6 2.5 262144 2.53 36 Yes No
Kimi-K2-Instruct-0905
together
1 3 262144 0.63 55 Yes Yes
Qwen3-VL-8B-Instruct
novita
0.08 0.5 131072 1.16 58 Yes Yes
Qwen3-8B
nscale
0.07 0.18 40960 1.13 58 Yes No
Kimi-K2-Instruct
novita
cheapest
0.57 2.3 131072 0.97 30 Yes Yes
Kimi-K2-Instruct
nebius
0.5 2.4 131072 0.52 49 Yes Yes
Kimi-K2-Instruct
together
1 3 131072 0.83 44 Yes Yes
Kimi-K2-Instruct
fireworks-ai
fastest
0.6 2.5 131072 0.87 49 Yes No
Llama-3.2-3B-Instruct
novita
cheapest
0.03 0.05 32768 0.79 124 Yes No
Llama-3.2-3B-Instruct
sambanova
- - - - - - -
Llama-3.2-3B-Instruct
hyperbolic
0.1 0.1 131072 0.79 129 No No
Llama-3.2-3B-Instruct
together
fastest
0.06 0.06 131072 1.07 143 Yes Yes
Qwen3-4B-Instruct-2507
nscale
0.01 0.03 262144 0.82 64 Yes No
Qwen3-Coder-30B-A3B-Instruct
nebius
cheapest fastest
0.1 0.3 262144 0.41 122 Yes Yes
Qwen3-Coder-30B-A3B-Instruct
fireworks-ai
- - - - - - -
Qwen3-Coder-30B-A3B-Instruct
scaleway
- - - 0.46 102 Yes No
DeepSeek-R1
novita
0.7 2.5 64000 0.82 27 Yes No
DeepSeek-R1
sambanova
fastest
- - - 1.03 113 Yes No
DeepSeek-R1
hyperbolic
cheapest
2 2 163840 0.91 56 No No
DeepSeek-R1
together
3 7 163840 0.56 62 No Yes
DeepSeek-R1
fireworks-ai
- - - - - - -
Meta-Llama-3-8B-Instruct
groq
- - - - - - -
Meta-Llama-3-8B-Instruct
novita
0.04 0.04 8192 0.76 75 No No
Meta-Llama-3-8B-Instruct
together
- - - - - - -
Qwen3-VL-30B-A3B-Instruct
novita
0.2 0.7 131072 0.93 78 Yes Yes
SmolLM3-3B
hf-inference
- - - 0.23 76 Yes Yes
Qwen2.5-7B-Instruct
together
0.3 0.3 32768 0.29 128 Yes Yes
DeepSeek-V3.2-Exp
novita
0.27 0.41 163840 0.84 31 Yes Yes
Apertus-8B-Instruct-2509
publicai
- - - 0.90 110 No Yes
Llama-3.2-1B-Instruct
novita
- - 131000 0.71 204 No No
Llama-3.2-1B-Instruct
sambanova
- - - - - - -
Qwen3-14B
nscale
0.07 0.2 40960 0.98 47 Yes Yes
Llama-3.3-70B-Instruct
groq
0.59 0.79 131072 0.19 327 Yes No
Llama-3.3-70B-Instruct
novita
cheapest
0.13 0.39 131072 0.66 23 Yes No
Llama-3.3-70B-Instruct
nebius
0.25 0.75 131072 0.45 118 Yes Yes
Llama-3.3-70B-Instruct
cerebras
fastest
0.85 1.2 - 0.29 1092 Yes No
Llama-3.3-70B-Instruct
sambanova
0.6 1.2 131072 0.99 245 Yes Yes
Llama-3.3-70B-Instruct
nscale
0.4 0.4 131072 0.94 16 No Yes
Llama-3.3-70B-Instruct
hyperbolic
0.4 0.4 131072 1.21 141 No No
Llama-3.3-70B-Instruct
together
0.88 0.88 131072 0.40 155 Yes Yes
Llama-3.3-70B-Instruct
fireworks-ai
0.9 0.9 131072 0.80 124 No No
Llama-3.3-70B-Instruct
scaleway
- - - 0.96 36 Yes Yes
Qwen2.5-VL-7B-Instruct
hyperbolic
0.2 0.2 32768 0.50 101 No No
Qwen3-VL-235B-A22B-Thinking
novita
0.98 3.95 131072 1.07 42 No No
GLM-4.5-Air
novita
cheapest
0.13 0.85 131072 1.13 63 Yes No
GLM-4.5-Air
nebius
fastest
0.2 1.2 131072 0.35 69 Yes Yes
GLM-4.5-Air
fireworks-ai
- - - - - - -
GLM-4.5-Air
zai-org
- - - 3.76 49 Yes No
Qwen3-Next-80B-A3B-Instruct
novita
0.15 1.5 131072 0.69 139 Yes No
Qwen3-Next-80B-A3B-Instruct
hyperbolic
cheapest fastest
0.3 0.3 262144 0.63 168 Yes No
Qwen3-Next-80B-A3B-Instruct
together
0.15 1.5 262144 0.88 146 Yes Yes
GLM-4.5V
novita
cheapest
0.6 1.8 65536 1.54 56 Yes No
GLM-4.5V
zai-org
fastest
- - - 2.44 62 Yes No
DeepSeek-R1-Distill-Qwen-1.5B
nscale
0.1 0.1 131072 0.97 136 No No
DeepSeek-R1-0528-Qwen3-8B
novita
0.06 0.09 128000 0.77 73 No No
Qwen3-235B-A22B-Instruct-2507
novita
cheapest
0.09 0.58 131072 1.11 31 Yes Yes
Qwen3-235B-A22B-Instruct-2507
nebius
0.2 0.6 262144 2.18 17 Yes Yes
Qwen3-235B-A22B-Instruct-2507
cerebras
fastest
0.6 1.2 - 0.34 483 Yes No
Qwen3-235B-A22B-Instruct-2507
nscale
0.2 0.6 32768 1.21 24 Yes Yes
Qwen3-235B-A22B-Instruct-2507
hyperbolic
2 2 262144 0.84 45 Yes No
Qwen3-235B-A22B-Instruct-2507
together
0.2 0.6 262144 0.88 39 Yes Yes
Qwen3-235B-A22B-Instruct-2507
fireworks-ai
0.22 0.88 262144 2.65 15 Yes No
Qwen3-235B-A22B-Instruct-2507
scaleway
- - - 0.49 81 Yes Yes
gemma-3-27b-it
nebius
cheapest fastest
0.2 0.6 110000 0.48 75 No Yes
gemma-3-27b-it
scaleway
- - - 0.60 43 Yes No
DeepSeek-R1-Distill-Qwen-7B
nscale
0.15 0.15 131072 0.87 65 No No
gpt-oss-safeguard-20b
groq
- - 131072 0.51 606 Yes No
Qwen3-30B-A3B-Instruct-2507
nebius
0.1 0.3 262144 0.40 98 Yes Yes
DeepSeek-V3-0324
novita
0.27 1.12 163840 0.92 35 Yes Yes
DeepSeek-V3-0324
nebius
fastest
0.75 2.25 32768 1.17 137 No No
DeepSeek-V3-0324
sambanova
3 4.5 131072 1.94 127 Yes Yes
DeepSeek-V3-0324
hyperbolic
1.25 1.25 163840 1.08 29 No No
DeepSeek-V3-0324
together
1.25 1.25 131072 0.96 41 Yes Yes
DeepSeek-V3-0324
fireworks-ai
cheapest
0.9 0.9 163840 0.83 57 Yes No
Llama-4-Scout-17B-16E-Instruct
groq
fastest
0.11 0.34 131072 0.19 373 Yes No
Llama-4-Scout-17B-16E-Instruct
novita
0.1 0.5 131072 1.01 33 No No
Llama-4-Scout-17B-16E-Instruct
sambanova
- - - - - - -
Llama-4-Scout-17B-16E-Instruct
nscale
cheapest
0.09 0.29 890000 0.82 33 Yes Yes
Llama-4-Scout-17B-16E-Instruct
together
0.18 0.59 1048576 0.35 76 Yes Yes
Llama-4-Scout-17B-16E-Instruct
fireworks-ai
0.15 0.6 1048576 0.77 52 Yes No
DeepSeek-V3
novita
0.4 1.3 64000 1.08 33 Yes No
DeepSeek-V3
together
cheapest fastest
1.25 1.25 131072 1.09 38 Yes Yes
DeepSeek-V3
fireworks-ai
- - - - - - -
GLM-4.5
novita
0.6 2.2 131072 0.74 40 Yes No
GLM-4.5
nebius
0.6 2.2 131072 0.52 37 Yes Yes
GLM-4.5
fireworks-ai
cheapest fastest
0.55 2.19 131072 0.88 87 Yes No
GLM-4.5
zai-org
- - - 3.25 50 Yes No
Qwen3-VL-235B-A22B-Instruct
novita
0.3 1.5 131072 0.86 38 Yes Yes
gemma-2-2b-it
nebius
0.02 0.06 8192 0.31 166 No Yes
ERNIE-4.5-VL-424B-A47B-Base-PT
novita
0.42 1.25 123000 1.50 39 No No
DeepSeek-V3.1-Terminus
novita
0.27 1 131072 1.11 33 No Yes
Qwen3-Coder-480B-A35B-Instruct
novita
cheapest
0.29 1.2 262144 0.92 40 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
nebius
fastest
0.4 1.8 262144 0.51 63 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
cerebras
- - - - - - -
Qwen3-Coder-480B-A35B-Instruct
hyperbolic
2 2 262144 1.60 60 Yes No
Qwen3-Coder-480B-A35B-Instruct
together
2 2 262144 0.70 38 Yes Yes
Qwen3-Coder-480B-A35B-Instruct
fireworks-ai
0.45 1.8 262144 1.29 38 No No
Qwen3-32B
groq
0.29 0.59 131072 0.20 258 Yes No
Qwen3-32B
novita
0.1 0.45 40960 0.44 84 No No
Qwen3-32B
nebius
0.1 0.3 40960 0.66 45 Yes No
Qwen3-32B
cerebras
fastest
0.4 0.8 - 0.36 944 No No
Qwen3-32B
sambanova
0.4 0.8 32768 2.79 189 Yes Yes
Qwen3-32B
nscale
cheapest
0.08 0.25 40960 1.25 24 Yes No
Qwen3-Next-80B-A3B-Thinking
novita
0.15 1.5 131072 0.95 110 Yes No
Qwen3-Next-80B-A3B-Thinking
hyperbolic
cheapest fastest
0.3 0.3 262144 0.71 171 Yes No
Qwen3-Next-80B-A3B-Thinking
together
0.15 1.5 262144 0.93 162 Yes Yes
DeepSeek-R1-Distill-Qwen-14B
novita
cheapest fastest
0.15 0.15 32768 1.22 62 No No
DeepSeek-R1-Distill-Qwen-14B
nscale
0.2 0.2 131072 0.89 37 No Yes
Llama-4-Maverick-17B-128E-Instruct
groq
cheapest
0.2 0.6 131072 2.02 219 Yes No
Llama-4-Maverick-17B-128E-Instruct
sambanova
fastest
0.63 1.8 131072 1.38 333 Yes Yes
Llama-4-Maverick-17B-128E-Instruct
fireworks-ai
0.22 0.88 1048576 0.61 72 Yes No
Qwen3-4B-Thinking-2507
nscale
0.01 0.03 262144 1.04 80 Yes No
Qwen3-VL-30B-A3B-Thinking
novita
0.2 1 131072 0.82 102 Yes Yes
Qwen2.5-Coder-7B-Instruct
nscale
0.01 0.03 131072 0.97 60 No Yes
Qwen3-235B-A22B
novita
0.2 0.8 40960 1.43 38 No No
Qwen3-235B-A22B
nscale
cheapest
0.2 0.6 32000 1.09 23 Yes Yes
Qwen3-235B-A22B
together
0.2 0.6 40960 0.50 37 Yes Yes
Qwen3-235B-A22B
fireworks-ai
fastest
0.22 0.88 131072 0.94 48 Yes No
DeepSeek-V3.1
novita
cheapest
0.27 1 131072 1.44 25 Yes No
DeepSeek-V3.1
together
fastest
0.6 1.7 131072 1.33 97 Yes No
DeepSeek-V3.1
fireworks-ai
- - 163840 0.79 80 Yes No
c4ai-command-a-03-2025
cohere
- - - 0.33 50 Yes No
Qwen3-30B-A3B
novita
cheapest
0.09 0.45 40960 0.85 100 No No
Qwen3-30B-A3B
fireworks-ai
fastest
0.15 0.6 131072 1.17 132 Yes No
DeepSeek-R1-Distill-Llama-8B
novita
- - - - - - -
DeepSeek-R1-Distill-Llama-8B
nscale
0.05 0.05 131072 0.86 57 No Yes
NVIDIA-Nemotron-Nano-12B-v2
nebius
0.07 0.2 131072 0.47 122 No Yes
Qwen3-30B-A3B-Thinking-2507
nebius
0.1 0.3 262144 0.41 107 Yes Yes
gemma-2-9b-it
groq
- - - - - - -
gemma-2-9b-it
nebius
0.03 0.09 8192 0.39 117 No Yes
DeepSeek-R1-Distill-Llama-70B
groq
- - - - - - -
DeepSeek-R1-Distill-Llama-70B
novita
0.8 0.8 8192 2.82 29 No Yes
DeepSeek-R1-Distill-Llama-70B
sambanova
fastest
0.7 1.4 131072 0.89 201 No No
DeepSeek-R1-Distill-Llama-70B
nscale
cheapest
0.75 0.75 131072 0.99 16 No No
DeepSeek-R1-Distill-Llama-70B
scaleway
- - - 0.83 20 No Yes
Llama-4-Maverick-17B-128E-Instruct-FP8
novita
cheapest
0.17 0.85 1048576 0.90 20 No No
Llama-4-Maverick-17B-128E-Instruct-FP8
together
fastest
0.27 0.85 1048576 0.38 72 Yes Yes
Qwen2.5-Coder-32B-Instruct
nscale
cheapest
0.06 0.2 131072 0.99 27 No Yes
Qwen2.5-Coder-32B-Instruct
hyperbolic
fastest
0.2 0.2 32768 0.94 77 No No
Qwen2.5-Coder-32B-Instruct
together
- - - - - - -
Qwen2.5-Coder-32B-Instruct
scaleway
- - - 0.45 38 Yes No
Qwen2.5-72B-Instruct
novita
cheapest
0.38 0.4 32000 0.67 39 Yes No
Qwen2.5-72B-Instruct
hyperbolic
0.4 0.4 131072 1.61 71 Yes No
Qwen2.5-72B-Instruct
together
fastest
1.2 1.2 131072 0.42 79 Yes Yes
Qwen2.5-72B-Instruct
fireworks-ai
- - - - - - -
GLM-4.5V-FP8
zai-org
- - - 2.55 61 Yes No
Llama-Guard-4-12B
groq
0.2 0.2 131072 0.32 6 No No
Arch-Router-1.5B
hf-inference
- - - 0.26 54 No Yes
L3-70B-Euryale-v2.1
novita
1.48 1.48 8192 0.82 34 No No
Llama-3.1-70B-Instruct
fireworks-ai
0.9 0.9 131072 0.47 128 No No
Qwen2.5-VL-72B-Instruct
nebius
0.25 0.75 32000 0.44 36 No Yes
Qwen2.5-VL-72B-Instruct
hyperbolic
cheapest fastest
0.6 0.6 32768 0.60 44 No No
ERNIE-4.5-VL-28B-A3B-PT
novita
0.14 0.56 30000 0.80 77 No No
ERNIE-4.5-21B-A3B-PT
novita
0.07 0.28 120000 1.13 79 No No
Baichuan-M2-32B
novita
0.07 0.07 131072 1.64 42 No Yes
DeepSeek-R1-0528
novita
0.7 2.5 163840 0.76 30 Yes No
DeepSeek-R1-0528
nebius
cheapest
0.8 2.4 163840 0.63 28 No Yes
DeepSeek-R1-0528
sambanova
fastest
5 7 131072 0.72 204 Yes No
DeepSeek-R1-0528
hyperbolic
3 3 163840 0.83 57 No No
DeepSeek-R1-0528
together
3 7 163840 0.58 45 No Yes
DeepSeek-R1-0528
fireworks-ai
3 8 163840 1.05 33 Yes No
Meta-Llama-3-70B-Instruct
groq
- - - - - - -
Meta-Llama-3-70B-Instruct
novita
0.51 0.74 8192 0.76 28 No Yes
Meta-Llama-3-70B-Instruct
hyperbolic
cheapest
0.4 0.4 8192 0.92 89 No No
Meta-Llama-3-70B-Instruct
together
fastest
0.88 0.88 8192 0.39 102 No Yes
QwQ-32B
groq
- - - - - - -
QwQ-32B
nebius
- - - - - - -
QwQ-32B
sambanova
- - - - - - -
QwQ-32B
nscale
cheapest
0.18 0.2 131072 0.94 27 Yes Yes
QwQ-32B
hyperbolic
fastest
0.4 0.4 131072 1.27 59 No No
QwQ-32B
fireworks-ai
- - - - - - -
Qwen3-235B-A22B-Thinking-2507
novita
fastest
0.3 3 131072 1.05 34 Yes No
Qwen3-235B-A22B-Thinking-2507
cerebras
- - - - - - -
Qwen3-235B-A22B-Thinking-2507
fireworks-ai
cheapest
0.22 0.88 262144 1.00 33 Yes No
Qwen2.5-VL-32B-Instruct
fireworks-ai
0.22 0.88 128000 0.58 62 No No
Qwen3-Coder-480B-A35B-Instruct-FP8
together
2 2 262144 0.63 40 Yes Yes
AFM-4.5B
together
0.048 0.15 65536 0.70 165 No Yes
command-a-translate-08-2025
cohere
- - - 0.37 61 Yes No
aya-expanse-32b
cohere
- - - 0.29 41 No No
c4ai-command-r7b-12-2024
cohere
- - - 0.29 108 Yes No
GLM-4.6-FP8
zai-org
- - - 2.78 57 Yes No
GLM-4-32B-0414
novita
0.55 1.66 32000 1.10 37 No Yes
DeepSeek-Prover-V2-671B
novita
0.7 2.5 160000 1.21 26 No No
Apertus-70B-Instruct-2509
publicai
- - - 1.13 37 Yes Yes
MiniMax-M1-80k
novita
0.55 2.2 1000000 1.47 63 Yes No
ERNIE-4.5-0.3B-PT
novita
- - 120000 1.01 102 No No
L3-8B-Stheno-v3.2
novita
0.05 0.05 8192 0.75 64 No No
GLM-4.1V-9B-Thinking
novita
0.035 0.138 65536 0.80 67 No No
Qwen2.5-Coder-3B-Instruct
nscale
0.01 0.03 32768 1.57 3 No Yes
Hermes-4-70B
nebius
0.13 0.4 131072 0.38 78 No No
L3-8B-Lunaris-v1
novita
0.05 0.05 8192 0.74 65 No No
Llama-3.1-405B-Instruct
sambanova
- - - - - - -
Llama-3.1-405B-Instruct
fireworks-ai
3 3 131072 0.71 60 Yes No
Mixtral-8x22B-Instruct-v0.1
nscale
cheapest
1.2 1.2 65536 1.17 25 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
GLM-4.5-Air-FP8
together
0.2 1.1 131072 0.33 60 Yes Yes
aya-vision-32b
cohere
- - - 0.40 56 No No
ERNIE-4.5-300B-A47B-Base-PT
novita
0.28 1.1 123000 1.00 29 No Yes
DeepSeek-R1-Distill-Qwen-32B
novita
cheapest fastest
0.3 0.3 64000 0.54 77 No Yes
DeepSeek-R1-Distill-Qwen-32B
nscale
0.3 0.3 131072 1.00 25 No Yes
c4ai-command-r-08-2024
cohere
- - - 0.27 47 Yes No
command-a-reasoning-08-2025
cohere
- - - 0.25 89 Yes No
cogito-v2-preview-deepseek-671B-MoE
together
1.25 1.25 163840 0.44 42 No Yes
cogito-v2-preview-llama-405B
together
3.5 3.5 32768 1.12 26 Yes Yes
cogito-v2-preview-llama-109B-MoE
together
0.18 0.59 32767 0.76 77 Yes Yes
cogito-v2-preview-llama-70B
together
0.88 0.88 32768 0.63 52 Yes Yes
command-a-vision-07-2025
cohere
- - - 0.33 45 No No
Llama-3_1-Nemotron-Ultra-253B-v1
nebius
0.6 1.8 131072 0.52 36 No Yes
Llama-3.3-Swallow-70B-Instruct-v0.4
sambanova
0.6 1.2 131072 1.56 177 No Yes
Hermes-4-405B
nebius
1 3 131072 0.43 37 No No
Hermes-3-Llama-3.1-70B
hyperbolic
0.4 0.4 12288 0.47 30 No No
marin-8b-instruct
together
0.18 0.18 4096 0.28 174 No Yes
WizardLM-2-8x22B
novita
0.62 0.62 65535 0.47 41 No No
Gemma-SEA-LION-v4-27B-IT
publicai
- - - 1.66 48 No Yes
Hermes-2-Pro-Llama-3-8B
novita
0.14 0.14 8192 0.82 108 No No
Qwen2.5-Coder-7B
nebius
0.03 0.09 32768 0.37 188 No Yes
Dobby-Unhinged-Llama-3.3-70B
fireworks-ai
0.9 0.9 131072 0.49 50 No No
Qwen3-235B-A22B-FP8
together
0.2 0.6 40960 0.60 35 Yes Yes