NVIDIA · datacenter

Tesla P100 16GB

Tesla P100 16GB has 16 GB of VRAM at 732 GB/s — about 14.88 GiB usable after driver and compositor overhead. 1400 of 2118 indexed models fit at 64K context with f16 KV.

Spec sheet· bandwidth, theoreticalFrom the file· fit from summed bytesPredicted· speed
Memory
16 GB
HBM2
Bandwidth
732 GB/s
4096-bit bus
Tensor FP16
—
dense
TDP
250 W
Context4K8K16K32K64K128K
KV cachef16q8_0q4_0quantizing the KV cache is a ~2× lever on the dominant term at long context
text 1163vision language 136embedding 26video 15audio tts 21audio asr 38image 1

What fits at 64K context

largest quantization that fits, per model · 1400 of 2118 indexed
ModelBest quantParamsWeights●KV●Total in memory◐Headroom◐tok/s◐
GLM-4.7-FlashMoEQ2_K31.2B10.57 GiB3.30 GiB14.88 GiB0.00 GiB51±37%
AMALIA-9B-0626-DPOQ2_K9.2B3.35 GiB10.50 GiB14.88 GiB0.00 GiB30±22%
Olmo-3-7B-InstructQ4_K_M7.3B4.16 GiB9.69 GiB14.88 GiB0.00 GiB30±22%
Olmo-3-7B-ThinkI1-Q4_K_M7.3B4.16 GiB9.69 GiB14.88 GiB0.00 GiB30±22%
Pantheon-Reasoning-26B-A4B-1.1MoEQ2_K_L26.5B11.10 GiB2.79 GiB14.88 GiB0.00 GiB30±22%
Bonsai-8B-unpackedQ4_K_M8.2B4.84 GiB9.00 GiB14.87 GiB0.01 GiB30±22%
Mistral-7B-v0.3Q6_K_L7.2B5.83 GiB8.00 GiB14.87 GiB0.01 GiB30±22%
medgemma-27b-itI1-IQ2_S28.8B8.18 GiB5.61 GiB14.87 GiB0.01 GiB30±22%
gemma-3-27b-it-abliterated-refined-visionI1-IQ2_S27.4B8.18 GiB5.61 GiB14.87 GiB0.01 GiB30±22%
Nidum-Gemma-3-27B-it-UncensoredI1-IQ2_S27.4B8.18 GiB5.61 GiB14.87 GiB0.01 GiB30±22%
gemma-3-27b-it-abliteratedIQ2_S27.4B8.18 GiB5.61 GiB14.87 GiB0.01 GiB30±22%
AtomicGPT-gemma3-27bI1-IQ2_S27.4B8.18 GiB5.61 GiB14.87 GiB0.01 GiB30±22%
Unbound-v1.12.0-27BI1-IQ2_S27.4B8.18 GiB5.61 GiB14.87 GiB0.01 GiB30±22%
Mira-v1.12-Ties-27BI1-IQ2_S27.4B8.18 GiB5.61 GiB14.87 GiB0.01 GiB30±22%
gemma-3-27b-itIQ2_S27.4B8.18 GiB5.61 GiB14.87 GiB0.01 GiB30±22%
Medgamma27BI1-IQ2_S27.0B8.18 GiB5.61 GiB14.87 GiB0.01 GiB30±22%
granite-20b-code-instruct-8kQ5_K_M20.1B13.79 GiB0.00 GiB14.87 GiB0.01 GiB30±22%
granite-20b-code-base-8kI1-Q5_K_M20.1B13.79 GiB0.00 GiB14.87 GiB0.01 GiB30±22%
granite-34b-code-base-8kI1-IQ3_S33.7B13.79 GiB0.00 GiB14.87 GiB0.01 GiB30±22%
Falcon3-10B-InstructI1-IQ3_XXS10.3B3.80 GiB10.00 GiB14.86 GiB0.02 GiB30±22%
Skywork-R1V3-38BIQ3_M38.4B13.79 GiB0.00 GiB14.86 GiB0.02 GiB30±22%
Huihui-Qwen3.5-35B-A3B-abliteratedMoEI1-IQ3_XXS36.0B12.60 GiB1.25 GiB14.86 GiB0.02 GiB96±37%
Qwen3.5-35B-A3B-BaseMoEI1-IQ3_XXS36.0B12.60 GiB1.25 GiB14.86 GiB0.02 GiB96±37%
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-DistilledMoEI1-IQ3_XXS36.0B12.60 GiB1.25 GiB14.86 GiB0.02 GiB96±37%
Qwen3.6-35B-A3B-REAM-160-ru-agentMoEIQ4_NL23.6B12.60 GiB1.25 GiB14.86 GiB0.02 GiB88±37%
gemma-4-12BQ6_K_M12.0B9.34 GiB4.47 GiB14.86 GiB0.02 GiB30±22%
Pantheon-Reasoning-27BIQ2_S27.8B9.79 GiB4.00 GiB14.85 GiB0.03 GiB30±22%
Qwen3.5-27BIQ2_S27.8B9.79 GiB4.00 GiB14.85 GiB0.03 GiB30±22%
Salience-1.5-FlashMoEIQ2_XXS31.1B7.85 GiB6.00 GiB14.85 GiB0.03 GiB34±37%
Qwen3-14BUD-IQ1_M14.8B3.79 GiB10.00 GiB14.85 GiB0.03 GiB30±22%
Aurora-Code-1MoEI1-IQ3_M34.7B12.59 GiB1.25 GiB14.84 GiB0.04 GiB96±37%
ZAYA1-8B-CoderMoEQ8_08.8B8.83 GiB5.00 GiB14.84 GiB0.04 GiB30±22%
Nemotron-3-Embed-8B-BF16Q5_K_M8.0B5.30 GiB8.50 GiB14.84 GiB0.04 GiB30±22%
Ministral-3-14B-Instruct-2512UD-IQ2_XXS13.9B3.78 GiB10.00 GiB14.83 GiB0.05 GiB30±22%
Ministral-3-14B-Reasoning-2512UD-IQ2_XXS13.9B3.78 GiB10.00 GiB14.83 GiB0.05 GiB30±22%
Qwen3.5-35B-A3BMoEQ2_K36.0B12.58 GiB1.25 GiB14.83 GiB0.05 GiB96±37%
Qwen3.6-35B-A3BMoEQ2_K36.0B12.58 GiB1.25 GiB14.83 GiB0.05 GiB96±37%
Qwen3.6-27B-Heretic2-Uncensored-Finetune-ThinkingIQ2_M27.4B9.77 GiB4.00 GiB14.83 GiB0.05 GiB30±22%
LFM2-24B-A2BMoEIQ4_NL23.8B12.56 GiB1.25 GiB14.82 GiB0.06 GiB83±37%
granite-4.0-h-smallMoEIQ3_XS32.2B12.83 GiB1.00 GiB14.82 GiB0.06 GiB67±37%
GLM-4.7-Flash-REAP-23B-A3BMoEQ3_K_M23.0B10.50 GiB3.30 GiB14.81 GiB0.07 GiB49±37%
North-Mini-Code-1.0MoEUD-IQ3_S30.5B11.89 GiB1.94 GiB14.81 GiB0.07 GiB69±37%
Qwopus3.6-27B-CoderIQ2_M27.8B9.74 GiB4.00 GiB14.80 GiB0.08 GiB30±22%
Anubis-Mini-8B-v1Q5_K_L8.0B5.76 GiB8.00 GiB14.80 GiB0.08 GiB30±22%
SmolVLM-InstructQ8_02.2B1.80 GiB12.00 GiB14.79 GiB0.09 GiB30±22%
SmolLM2-1.7B-Instruct-UncensoredQ8_01.8B1.80 GiB12.00 GiB14.79 GiB0.09 GiB30±22%
HomunculusIQ2_XS12.5B3.74 GiB10.00 GiB14.79 GiB0.09 GiB30±22%
Apertus-8B-Instruct-2509Q5_K_L8.1B5.72 GiB8.00 GiB14.79 GiB0.09 GiB30±22%
Hy-MT2-7BQ6_K8.0B5.74 GiB8.00 GiB14.78 GiB0.10 GiB30±22%
Hunyuan-7B-InstructQ6_K7.5B5.74 GiB8.00 GiB14.78 GiB0.10 GiB30±22%
Trinity-MiniMoEQ3_K_L26.1B12.66 GiB1.12 GiB14.78 GiB0.10 GiB87±37%
llm-jp-4-8b-instructQ5_K_M8.6B5.73 GiB8.00 GiB14.77 GiB0.11 GiB30±22%
granite-8b-code-base-4kQ4_18.1B4.73 GiB9.00 GiB14.77 GiB0.11 GiB30±22%
Dolphin3.0-Qwen2.5-3bF323.1B11.50 GiB2.25 GiB14.76 GiB0.12 GiB30±22%
VibeThinker-3BF323.1B11.50 GiB2.25 GiB14.76 GiB0.12 GiB30±22%
Qwen2.5-3B-InstructF323.1B11.50 GiB2.25 GiB14.76 GiB0.12 GiB30±22%
Qwen2.5-3BF323.1B11.50 GiB2.25 GiB14.76 GiB0.12 GiB30±22%
Huihui-gemma-3n-E4B-it-abliteratedF167.8B12.80 GiB0.93 GiB14.76 GiB0.12 GiB30±22%
gemma-3n-E4B-itF167.8B12.80 GiB0.93 GiB14.76 GiB0.12 GiB30±22%
Mistral-7B-v0.1KV unresolvedIQ4_NL7.2B5.72 GiB8.00 GiB14.76 GiB0.12 GiB30±22%
●From the file◐Predictedwhat these mean

Speed is modeled, not measured: decode is memory-bandwidth bound, so tokens per second is bytes read per token against achievable bandwidth. Mixture-of-experts models carry a wider band because only the routed experts are read each step, and few have been measured publicly.

Questions people ask

What AI models can a Tesla P100 16GB run?
1400 of 2118 indexed open-weight models fit a Tesla P100 16GB at 65,536 context with f16 KV cache, the largest being GLM-4.7-Flash at Q2_K. That covers text, vision-language, image, video and speech models.
How much usable memory does a Tesla P100 16GB actually have?
Its nameplate is 16 GB, but about 14.88 GiB is available to a model once driver and compositor overhead is accounted for.
Is a Tesla P100 16GB fast for local AI?
Its memory bandwidth is 732 GB/s, and that figure — not teraflops — is what governs token generation speed. Capacity decides what you can run; bandwidth decides how fast it runs.