NVIDIA· BLACKWELL 2.0

NVIDIA RTX PRO 6000 Blackwell

VRAM
96 GB
FLAGSHIP
BANDWIDTH
1790
GB/S
MODELS Q4
297/331
90%
7B Q4 SPEED
~205
BLAZING
▸ MODEL COVERAGE @ Q490% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

Average speeds at Q4 quantization. Actual performance varies by model architecture and context length.

3B
~477
TOK/S
7B
~205
TOK/S
14B
~102
TOK/S
32B
~45
TOK/S
70B
~20
TOK/S
▸ SPECIFICATIONS
VRAM
96 GB
BANDWIDTH
1790 GB/s
FP16 COMPUTE
126 TFLOPS
TDP
600W
MEMORY
GDDR7
ARCHITECTURE
Blackwell 2.0
CUDA CORES
24,064
TENSOR CORES
752
PCIE
Gen 5 x16
MSRP
$9,999
271
FAST MODELS · >30 TOK/S
Real-time chat speed
297
USABLE · >10 TOK/S
Comfortable for all tasks
297
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ RENT IT IN THE CLOUD

Buying RTX PRO 6000 Blackwell costs $15–$40k and isn’t practical for most teams. Spin one up by the hour instead:

Spin up in ~60s. Pay by the second. Cancel anytime.

Some links are affiliate links — we may earn a small commission at no extra cost to you. This helps keep FitMyLLM free and independent.

▸ COMPATIBLE MODELS· 297
S
nomic-embed-text-v1.5 100M0.1B
EMBEDDING·8K CTX· CHAT
14320
TOK/S · 1% VRAM
S
GPT-2 124M0.124B
GPT2·1K CTX· CHAT
11548
TOK/S · 1% VRAM
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
10607
TOK/S · 1% VRAM
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
4275
TOK/S · 1% VRAM
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
4275
TOK/S · 1% VRAM
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
4275
TOK/S · 1% VRAM
S
GPT-2 Medium 345M0.345B
GPT2·1K CTX· CHAT
4151
TOK/S · 1% VRAM
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
3978
TOK/S · 1% VRAM
S
Falcon-H1 0.5B0.5B
FALCON·128K CTX· CHAT
2864
TOK/S · 1% VRAM
S
Qwen 1.5 0.5B0.5B
QWEN·32K CTX· CHAT
2864
TOK/S · 1% VRAM
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
2864
TOK/S · 1% VRAM
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
2521
TOK/S · 1% VRAM
S
Qwen3 0.6B0.6B
QWEN·32K CTX· CHAT· REASONING
2387
TOK/S · 1% VRAM
S
GPT-2 Large 774M0.774B
GPT2·1K CTX· CHAT
1850
TOK/S · 1% VRAM
S
Qwen 3.5 0.8B0.8B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
1790
TOK/S · 1% VRAM
S
Qwen3.5-0.8B0.9B
QWEN·256K CTX· CHAT
1591
TOK/S · 1% VRAM
S
Falcon3-1B1B
FALCON·32K CTX· CHAT
1432
TOK/S · 1% VRAM
S
InternLM2 1B1B
INTERNLM·32K CTX· CHAT
1432
TOK/S · 1% VRAM
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
1302
TOK/S · 1% VRAM
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
1193
TOK/S · 1% VRAM
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
1193
TOK/S · 1% VRAM
S
DeepSeek Coder 1.3B1.3B
DEEPSEEK·16K CTX· CODING
1102
TOK/S · 1% VRAM
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
1102
TOK/S · 1% VRAM
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
1102
TOK/S · 1% VRAM
S
Phi-1 1.3B1.3B
PHI·2K CTX· CODING
1102
TOK/S · 1% VRAM
S
Phi-1.5 1.3B1.3B
PHI·2K CTX· CHAT· CODING
1102
TOK/S · 1% VRAM
S
granite-4.0-h-tiny 6.9B6.9BMoE
GRANITE·128K CTX· CHAT
955
TOK/S · 5% VRAM
S
Falcon-H1 1.5B1.5B
FALCON·128K CTX· CHAT· CODING
955
TOK/S · 1% VRAM
S
GPT-2 XL 1.5B1.5B
GPT2·1K CTX· CHAT
955
TOK/S · 1% VRAM
S
Qwen2.5-Coder-1.5B1.5B
QWEN·32K CTX· CHAT· TOOL_USE· CODING
955
TOK/S · 1% VRAM
S
Qwen2 Math 1.5B1.5B
QWEN·4K CTX· REASONING
955
TOK/S · 1% VRAM
S
Qwen 2.5 1.5B1.5B
QWEN·32K CTX· CHAT· CODING
955
TOK/S · 1% VRAM
S
Yi Coder 1.5B1.5B
YI·125K CTX· CODING
955
TOK/S · 1% VRAM
S
stablelm-2-1_6b1.6B
STABLELM·4K CTX· CHAT
895
TOK/S · 2% VRAM
S
Qwen3 1.7B1.7B
QWEN·32K CTX· CHAT· REASONING
842
TOK/S · 2% VRAM
S
SmolLM2 1.7B1.71B
SMOLLM·8K CTX· CHAT
837
TOK/S · 2% VRAM
S
Qwen 1.5 1.8B1.8B
QWEN·32K CTX· CHAT
796
TOK/S · 2% VRAM
S
Moondream2 1.9B1.9B
OTHER·2K CTX· VISION· CHAT
754
TOK/S · 2% VRAM
S
Gemma 1 2B2B
GEMMA·8K CTX· CHAT
716
TOK/S · 2% VRAM
S
Granite 3.0 2B2B
GRANITE·128K CTX· CHAT· CODING
716
TOK/S · 2% VRAM
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your RTX PRO 6000 Blackwell.

▸ DEVICE UNDER TEST

NVIDIA RTX PRO 6000 Blackwell96 GB VRAM.

RTX PRO 6000 BLACKWELL SPEC
BRAND
NVIDIA
VRAM
96 GB GDDR7
BANDWIDTH
1790 GB/s
FP16 COMPUTE
126 TFLOPS
FP32 COMPUTE
126 TFLOPS
CUDA CORES
24,064
TENSOR CORES
752
TDP
600 W
ARCHITECTURE
Blackwell 2.0
MSRP
$9999
▸ AI CAPABILITY
297/ 331 models @ Q4

With 96 GB VRAM and 1790 GB/s bandwidth, this GPU handles models up to 132B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~205 tok/s.

§ 01TOP MODELS FOR RTX PRO 6000 BLACKWELL
297 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
DBRX 132B132B81.2 GB4046.3
Qwen3.5-122B-A10B125.1B77.0 GB1145.5
Pixtral Large 124B124B76.3 GB1239.3
Mistral-Large 123B123B75.7 GB1233.5
Devstral 2 123B123B75.7 GB1238.1
Qwen 3.5 122B A10B122B75.1 GB14356.8
Nemotron 3 Super 120B120B73.8 GB11957.3
Nemotron 3 Super 120B-A12B120B73.8 GB11953.2
Mistral Small 4 119B119B73.2 GB22050.2
GPT-OSS 120B117B72.0 GB28154.1
Command A 111B111B68.3 GB1327.6
GLM 4.5 Air110B67.7 GB11951.0
Qwen 1.5 110B110B67.7 GB1333.4
Llama 4 Scout 17B-16E109B67.1 GB8433.9
Sarvam 105B105B64.7 GB1448.0
Command-R+ 104B104B64.1 GB1452.7
Llama-3.2-90B-Vision-Instruct90B55.5 GB1648.5
Hunyuan A13B80B49.4 GB11081.1
Qwen3-Coder-Next80B49.4 GB47743.0
Qwen2.5-72B72.7B44.9 GB2039.7