NVIDIA· BLACKWELL 2.0

NVIDIA RTX PRO 2000 Blackwell

VRAM
16 GB
MID-RANGE
BANDWIDTH
288
GB/S
MODELS Q4
202/331
61%
7B Q4 SPEED
~33
FAST
▸ MODEL COVERAGE @ Q461% OF ALL
▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

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

3B
~77
TOK/S
7B
~33
TOK/S
14B
~16
TOK/S
32B
18.0GB NEEDED
70B
39.4GB NEEDED
▸ SPECIFICATIONS
VRAM
16 GB
BANDWIDTH
288 GB/s
FP16 COMPUTE
17 TFLOPS
TDP
70W
MEMORY
GDDR7
ARCHITECTURE
Blackwell 2.0
CUDA CORES
4,352
TENSOR CORES
136
PCIE
Gen 5 x8
MSRP
$1,249
132
FAST MODELS · >30 TOK/S
Real-time chat speed
202
USABLE · >10 TOK/S
Comfortable for all tasks
202
TOTAL COMPATIBLE
Fit in VRAM at Q4
▸ RENT IT IN THE CLOUD

Buying RTX PRO 2000 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· 202
S
nomic-embed-text-v1.5 100M0.1B
EMBEDDING·8K CTX· CHAT
2304
TOK/S · 3% VRAM
S
GPT-2 124M0.124B
GPT2·1K CTX· CHAT
1858
TOK/S · 4% VRAM
S
SmolLM2 135M0.135B
SMOLLM·2K CTX· CHAT
1707
TOK/S · 4% VRAM
S
bge-large-en-v1.5 335M0.335B
EMBEDDING·1K CTX· CHAT
688
TOK/S · 4% VRAM
S
mxbai-embed-large-v10.335B
EMBEDDING·1K CTX· EMBEDDING
688
TOK/S · 4% VRAM
S
Snowflake Arctic Embed L0.335B
EMBEDDING·1K CTX· EMBEDDING
688
TOK/S · 4% VRAM
S
GPT-2 Medium 345M0.345B
GPT2·1K CTX· CHAT
668
TOK/S · 4% VRAM
S
SmolLM2 360M0.36B
SMOLLM·8K CTX· CHAT
640
TOK/S · 4% VRAM
S
Falcon-H1 0.5B0.5B
FALCON·128K CTX· CHAT
461
TOK/S · 5% VRAM
S
Qwen 1.5 0.5B0.5B
QWEN·32K CTX· CHAT
461
TOK/S · 5% VRAM
S
Qwen 2.5 0.5B0.5B
QWEN·32K CTX· CHAT
461
TOK/S · 5% VRAM
S
BGE-M30.568B
EMBEDDING·8K CTX· EMBEDDING
406
TOK/S · 5% VRAM
S
Qwen3 0.6B0.6B
QWEN·32K CTX· CHAT· REASONING
384
TOK/S · 5% VRAM
S
GPT-2 Large 774M0.774B
GPT2·1K CTX· CHAT
298
TOK/S · 6% VRAM
S
Qwen 3.5 0.8B0.8B
QWEN·256K CTX· CHAT· CODING· MULTILINGUAL
288
TOK/S · 6% VRAM
S
Qwen3.5-0.8B0.9B
QWEN·256K CTX· CHAT
256
TOK/S · 6% VRAM
S
Falcon3-1B1B
FALCON·32K CTX· CHAT
230
TOK/S · 7% VRAM
S
InternLM2 1B1B
INTERNLM·32K CTX· CHAT
230
TOK/S · 7% VRAM
S
TinyLlama 1.1B1.1B
LLAMA·2K CTX· CHAT
209
TOK/S · 7% VRAM
S
LFM2.5-1.2B-Thinking1.2B
LFM·122K CTX· CHAT· REASONING· TOOL_USE
192
TOK/S · 8% VRAM
S
Llama-3.2-1B1.2B
LLAMA·4K CTX· CHAT
192
TOK/S · 8% VRAM
S
DeepSeek Coder 1.3B1.3B
DEEPSEEK·16K CTX· CODING
177
TOK/S · 8% VRAM
S
EXAONE-4.0-1.2B1.3B
EXAONE·64K CTX· CHAT
177
TOK/S · 8% VRAM
S
OPT 1.3B1.3B
OPT·2K CTX· CHAT
177
TOK/S · 8% VRAM
S
Phi-1 1.3B1.3B
PHI·2K CTX· CODING
177
TOK/S · 8% VRAM
S
Phi-1.5 1.3B1.3B
PHI·2K CTX· CHAT· CODING
177
TOK/S · 8% VRAM
S
granite-4.0-h-tiny 6.9B6.9BMoE
GRANITE·128K CTX· CHAT
154
TOK/S · 29% VRAM
S
Falcon-H1 1.5B1.5B
FALCON·128K CTX· CHAT· CODING
154
TOK/S · 9% VRAM
S
GPT-2 XL 1.5B1.5B
GPT2·1K CTX· CHAT
154
TOK/S · 9% VRAM
S
Qwen2.5-Coder-1.5B1.5B
QWEN·32K CTX· CHAT· TOOL_USE· CODING
154
TOK/S · 9% VRAM
S
Qwen2 Math 1.5B1.5B
QWEN·4K CTX· REASONING
154
TOK/S · 9% VRAM
S
Qwen 2.5 1.5B1.5B
QWEN·32K CTX· CHAT· CODING
154
TOK/S · 9% VRAM
S
Yi Coder 1.5B1.5B
YI·125K CTX· CODING
154
TOK/S · 9% VRAM
S
stablelm-2-1_6b1.6B
STABLELM·4K CTX· CHAT
144
TOK/S · 9% VRAM
S
Qwen3 1.7B1.7B
QWEN·32K CTX· CHAT· REASONING
136
TOK/S · 10% VRAM
S
SmolLM2 1.7B1.71B
SMOLLM·8K CTX· CHAT
135
TOK/S · 10% VRAM
S
Qwen 1.5 1.8B1.8B
QWEN·32K CTX· CHAT
128
TOK/S · 10% VRAM
S
Moondream2 1.9B1.9B
OTHER·2K CTX· VISION· CHAT
121
TOK/S · 10% VRAM
S
Gemma 1 2B2B
GEMMA·8K CTX· CHAT
115
TOK/S · 11% VRAM
S
Granite 3.0 2B2B
GRANITE·128K CTX· CHAT· CODING
115
TOK/S · 11% VRAM
▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your RTX PRO 2000 Blackwell.

▸ DEVICE UNDER TEST

NVIDIA RTX PRO 2000 Blackwell16 GB VRAM.

RTX PRO 2000 BLACKWELL SPEC
BRAND
NVIDIA
VRAM
16 GB GDDR7
BANDWIDTH
288 GB/s
FP16 COMPUTE
17 TFLOPS
FP32 COMPUTE
17 TFLOPS
CUDA CORES
4,352
TENSOR CORES
136
TDP
70 W
ARCHITECTURE
Blackwell 2.0
MSRP
$1249
▸ AI CAPABILITY
202/ 331 models @ Q4

With 16 GB VRAM and 288 GB/s bandwidth, this GPU handles models up to 22.2B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~33 tok/s.

§ 01TOP MODELS FOR RTX PRO 2000 BLACKWELL
202 FIT · SHOWING 20
MODELSIZEVRAM Q4TOK/SAVG
Codestral 22B22.2B14.1 GB1050.1
Devstral Small 22B22.2B14.1 GB1035.5
Mistral Small 22B22.2B14.1 GB1035.2
SOLAR-Pro 22B22.1B14.0 GB1044.2
ERNIE 4.5 21B A3B21B13.3 GB77
GPT-OSS 20B21B13.3 GB6452.9
InternLM2 20B19.8B12.6 GB1245.1
InternLM2.5 20B19.8B12.6 GB1250.9
Ling-lite 16.8B16.8B10.8 GB96
DeepSeek V2 Lite 16B16B10.3 GB9638.0
DeepSeek-Coder-V2-Lite 15.7B15.7B10.1 GB9643.0
DeepSeek-VL2 Small 16B15.7B10.1 GB9643.1
StarCoder 15B15.5B10.0 GB1521.0
StarCoder2 15B15B9.7 GB1526.5
DeepSeek R1 Distill Qwen 14B14.8B9.5 GB1643.9
DeepCoder 14B14.8B9.5 GB1638.7
Qwen2.5-Coder-14B14.8B9.5 GB1641.3
Qwen2.5-14B14.8B9.5 GB1641.3
Qwen3 14B14.8B9.5 GB1645.7
Ministral 3 14B14B9.0 GB1625.9