NVIDIA · Blackwell Ultra

Best AI Models for NVIDIA B300 (288 GB)

Runs everything up to 120B MoE well.

288 GB HBM3e8000 GB/s3750 TFLOPS FP161400 WBlackwell Ultra 2025

Datacenter Blackwell Ultra — rack/cloud only, not a desktop card. Listed for comparison.

What LLMs can the B300 run?

#	Model	Speed	Quant · VRAM
1	MiMo V2.6 Flash RLXiaomiHow to run → Q4_K_M · 186.5 GB · 229 t/s	229 tok/s	Q4_K_M · 186.5 GB
2	DeepSeek V4 Flash 0731DeepSeek Q4_K_M · 183.0 GB · 181 t/s	181 tok/s	Q4_K_M · 183.0 GB
3	GLM 5.3 FlashZ.ai Q4_K_M · 205.2 GB · 217 t/s	217 tok/s	Q4_K_M · 205.2 GB
4	Qwen3.8 27BAlibaba Q4_K_M · 17.9 GB · 299 t/s	299 tok/s	Q4_K_M · 17.9 GB
5	Hy3Tencent Q4_K_M · 182.3 GB · 147 t/s	147 tok/s	Q4_K_M · 182.3 GB

#	Model	Speed	Quant · VRAM
1	MiMo V2.6 Flash RLXiaomiHow to run → Q4_K_M · 186.5 GB · 229 t/s	229 tok/s	Q4_K_M · 186.5 GB
2	DeepSeek V4 Flash 0731DeepSeek Q4_K_M · 183.0 GB · 181 t/s	181 tok/s	Q4_K_M · 183.0 GB
3	Qwen3.8 27BAlibaba Q4_K_M · 17.9 GB · 299 t/s	299 tok/s	Q4_K_M · 17.9 GB
4	GLM 5.3 FlashZ.ai Q4_K_M · 205.2 GB · 217 t/s	217 tok/s	Q4_K_M · 205.2 GB
5	Hy3Tencent Q4_K_M · 182.3 GB · 147 t/s	147 tok/s	Q4_K_M · 182.3 GB

#	Model	Speed	Quant · VRAM
1	DeepSeek V4 Flash 0731DeepSeekHow to run → Q4_K_M · 183.0 GB · 181 t/s	181 tok/s	Q4_K_M · 183.0 GB
2	GLM 5.3 FlashZ.ai Q4_K_M · 205.2 GB · 217 t/s	217 tok/s	Q4_K_M · 205.2 GB
3	Qwen3.8 27BAlibaba Q4_K_M · 17.9 GB · 299 t/s	299 tok/s	Q4_K_M · 17.9 GB
4	Inkling SmallThinking Machines Q4_K_M · 162.7 GB · 399 t/s	399 tok/s	Q4_K_M · 162.7 GB
5	Hy3Tencent Q4_K_M · 182.3 GB · 147 t/s	147 tok/s	Q4_K_M · 182.3 GB

#	Model	Speed ↓	Quant · VRAM
1	Qwen3.5 4BAlibabaHow to run → Q4_K_M · 3.4 GB · 1595 t/s	1595 tok/s	Q4_K_M · 3.4 GB
2	Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB · 818 t/s	818 tok/s	Q4_K_M · 6.6 GB
3	GPT OSS 20BOpenAI Q4_K_M · 13.1 GB · 550 t/s	550 tok/s	Q4_K_M · 13.1 GB
4	Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB · 459 t/s	459 tok/s	Q4_K_M · 16.5 GB
5	Hy3Tencent Q4_K_M · 182.3 GB · 147 t/s	147 tok/s	Q4_K_M · 182.3 GB

#	Model	Speed	Quant · VRAM
1	GLM 5.3 FlashZ.aiHow to run → Q4_K_M · 205.2 GB · 217 t/s	217 tok/s	Q4_K_M · 205.2 GB
2	Qwen3.8 27BAlibaba Q4_K_M · 17.9 GB · 299 t/s	299 tok/s	Q4_K_M · 17.9 GB
3	Inkling SmallThinking Machines Q4_K_M · 162.7 GB · 399 t/s	399 tok/s	Q4_K_M · 162.7 GB
4	MiniMax M3MiniMax Q4_K_M · 258.0 GB · 179 t/s	179 tok/s	Q4_K_M · 258.0 GB
5	Qwen3.8 Flash NextAlibaba Q4_K_M · 109.0 GB · 102 t/s	102 tok/s	Q4_K_M · 109.0 GB

See all 433 models on the B300 →Best quant that fits · speeds estimated on this card

About the B300

The B300 runs everything up to 120B MoE well. Blackwell Ultra generation, released 2025.

GenerationBlackwell Ultrareleased 2025

B300 strengths and weaknesses

Strengths

Runs 120B MoE models: GPT OSS 120B at 378 tok/s in 70.8 GB
Room for long context: Llama 3.3 70B Instruct at Q4 uses 51.3 GB, leaving 236.7 GB free
Reads long prompts fast: A 4K-token prompt on MiMo V2.6 Flash RL starts answering in 82 ms
FP8 and NVFP4 run natively: Blackwell takes FP8 and NVFP4 checkpoints in vLLM as published

Weaknesses

1400 W under load: Plan a 2,800 W PSU; ≈$307 a year at 4 h a day

B300 tokens per second by model size

Output speed depends on memory bandwidth (8000 GB/s).

9BQwen3.5 9B · Q4_K_M · 6.6 GB
818tok/s
14BQwen3 14B · Q4_K_M · 11.9 GB
547tok/s
27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
299tok/s
35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
363tok/s
70BLlama 3.3 70B Instruct · Q4_K_M · 51.3 GB
112tok/s
120B MoEGPT OSS 120B · Q4_K_M · 70.8 GB
378tok/s

Estimated speeds: Q4_K_M, 4K context, one user. How we estimate

All 1341 models on the B300

Featured only

Best quant that fits, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with NVIDIA B300 — ranked by Score, recency and Fit
Model	Quant	VRAM	Speed	Context	Fit
Gemma 4 12B IT AEON Abliterated K4 BF1612.0BChatReasoningFunctions Q4_K_M·631.8 t/s	Q4_K_M	9.0 GB3%	631.8 t/s	262K	S100, Runs great
Gemma 4 31B IT DFlash31BChat Q4_K_M·274.7 t/s	Q4_K_M	19.1 GB7%	274.7 t/s	262K	S100, Runs great
LFM2.5 230M230MChatFunctions Q4_K_M·10400.0 t/s	Q4_K_M	0.6 GB0%	10400.0 t/s	128K	S100, Runs great
Tiny Phi3ForCausalLM 3.5514984Chat Q4_K_M·17333.3 t/s	Q4_K_M	0.5 GB0%	17333.3 t/s	131K	S100, Runs great
SmolVLM2 500M Video Instruct507MVision Q4_K_M·7536.2 t/s	Q4_K_M	0.9 GB0%	7536.2 t/s	8K	S100, Runs great
Dolphin Mistral 24B Venice Edition24.0BChat Q4_K_M·343.7 t/s	Q4_K_M	18.1 GB6%	343.7 t/s	131K	S100, Runs great
Nandi Mini 150M153MChat BF16·8254.0 t/s	BF16	0.6 GB0%	8254.0 t/s	2K	S100, Runs great
GLM 5.3 Flash BF16321.3BVisionFunctions Q4_K_M·216.9 t/s	Q4_K_M	205.2 GB71%	216.9 t/s	1049K	S100, Runs great
Olmo 3 32B Think32.2BChat Q4_K_M·257.7 t/s	Q4_K_M	21.5 GB7%	257.7 t/s	66K	S100, Runs great
Qwen3.6 35B A3B DFlash35BChat Q4_K_M·1467.2 t/s	Q4_K_M	21.5 GB7%	1467.2 t/s	262K	S100, Runs great
LFM2.5 8B A1B8.5BChatFunctions Q4_K_M·653.7 t/s	Q4_K_M	5.6 GB2%	653.7 t/s	128K	S100, Runs great
Qwen3 235B A22B235.1BChatFunctions Q4_K_M·129.2 t/s	Q4_K_M	142.9 GB50%	129.2 t/s	41K	S95, Runs great
XCurOS0.1 8B Instruct7.6BChatFunctions BF16·332.3 t/s	BF16	16.5 GB6%	332.3 t/s	33K	S100, Runs great
Qwen3 30B A3B Instruct 250730.5BChatFunctions Q4_K_M·329.5 t/s	Q4_K_M	19.4 GB7%	329.5 t/s	262K	S100, Runs great
MiniCPM5 1B1.1BChatFunctions Q4_K_M·5252.5 t/s	Q4_K_M	1.3 GB0%	5252.5 t/s	131K	S100, Runs great

Rent NVIDIA B300 in the cloud

Hourly rate on demand for one B300.

RunPod$5+ bonus credit
from$6.94/hr
Deploy

Cost per million tokens

Output-token cost on a B300 rented at $6.94/hr, one request at a time. Batch several users on the same card and the cost per token drops several-fold.

Model	Quant	Speed	Per 1M output
Inkling Small	Q4_K_M	399 tok/s	$4.84$0.039 input
MiMo V2.6 Flash RL	Q4_K_M	229 tok/s	$8.43$0.039 input
GLM 5.3 Flash	Q4_K_M	217 tok/s	$8.89$0.042 input
DeepSeek V4 Flash 0731	Q4_K_M	181 tok/s	$10.66$0.063 input
Hy3	Q4_K_M	147 tok/s	$13.16$0.048 input

B300 specs, power and PSU

Specs

Architecture: Blackwell Ultra
VRAM: 288 GB HBM3e
Memory bandwidth: 8000.0 GB/s
FP16 (dense): 3750.00 TFLOPS
CUDA cores: 20,480
Tensor cores: 640
Compute capability: 10.0
TDP: 1400 W
Released: 2025-08-01

B300 FAQ

What is the largest model the B300 can run?

Beam 1.0 501B A23B (501.3B) is the largest at 4-bit or better: at Q4_K_S it uses 285.2 GB of 288 GB, and runs at about 185 tok/s.

Can the B300 run MiMo V2.6 Flash RL?

Yes. MiMo V2.6 Flash RL fits at Q4_K_M, using 186.5 GB of 288 GB, and it is the best model that runs well on this card.

How many tokens per second does the B300 give?

About 229 tok/s on MiMo V2.6 Flash RL at Q4_K_M, with the first token after 0.1 s on a 4K-token prompt.

What power supply does the B300 need?

Plan a 2800 W PSU (2× the 1400 W TDP).

Is 288 GB enough for coding and agents?

Yes for coding: MiMo V2.6 Flash RL, the best of the 25 coding models that fit, runs at about 229 tok/s.

Best coding LLMs 48 GB VRAM GPUs with 288 GB or more RTX 5090 RTX 4090 RTX 3090