Tesla V100 32GB

NVIDIA Data Center (used)

VRAM
32 GB
Memory bandwidth
900 GB/s
fp16 compute
125 TFLOPS
Class
Workstation

Figures assume this GPU plus 32 GB of system RAM (a typical desktop pairing). "What runs on it" is judged at a 8,192-token context. Speeds are estimates, not measurements.

What runs on it

Model Sweet-spot quant Est. speed Community
DeepSeek-R1-Distill-Llama-8B deepseek-ai Q8_0 Runs fully on GPU @ 8K ctx 56–75 tok/s (estimate) no community data
DeepSeek-R1-Distill-Qwen-1.5B deepseek-ai Q8_0 Runs fully on GPU @ 8K ctx 254–338 tok/s (estimate) no community data
DeepSeek-R1-Distill-Qwen-14B deepseek-ai Q8_0 Runs fully on GPU @ 8K ctx 31–42 tok/s (estimate) no community data
DeepSeek-R1-Distill-Qwen-32B deepseek-ai Q4_K_M Runs fully on GPU @ 8K ctx 25–33 tok/s (estimate) no community data
DeepSeek-R1-Distill-Qwen-7B deepseek-ai Q8_0 Runs fully on GPU @ 8K ctx 63–84 tok/s (estimate) no community data
Devstral-Small-2-24B-Instruct-2512 mistralai Q8_0 Runs fully on GPU @ 8K ctx 20–27 tok/s (estimate) no community data
GLM-4.7-Flash zai-org Q6_K Runs fully on GPU @ 8K ctx no community data
Kimi-VL-A3B-Instruct moonshotai Q8_0 Runs fully on GPU @ 8K ctx no community data
Llama-3.1-8B-Instruct meta-llama Q8_0 Runs fully on GPU @ 8K ctx 56–75 tok/s (estimate) no community data
Mistral-Small-3.2-24B-Instruct-2506 mistralai Q8_0 Runs fully on GPU @ 8K ctx 20–27 tok/s (estimate) no community data
Phi-4-mini-instruct microsoft Q8_0 Runs fully on GPU @ 8K ctx 105–140 tok/s (estimate) no community data
Phi-4-reasoning microsoft Q8_0 Runs fully on GPU @ 8K ctx 31–42 tok/s (estimate) no community data
Qwen2.5-7B-Instruct Qwen Q8_0 Runs fully on GPU @ 8K ctx 63–84 tok/s (estimate) no community data
Qwen2.5-Omni-7B Qwen BF16 Runs fully on GPU @ 8K ctx 24–32 tok/s (estimate) no community data
Qwen2.5-VL-32B-Instruct Qwen Q4_K_M Runs fully on GPU @ 8K ctx 25–33 tok/s (estimate) no community data
Qwen3-14B Qwen Q8_0 Runs fully on GPU @ 8K ctx 32–42 tok/s (estimate) no community data
Qwen3-30B-A3B-Instruct-2507 Qwen Q4_K_M Runs fully on GPU @ 8K ctx no community data
Qwen3-32B Qwen Q4_K_M Runs fully on GPU @ 8K ctx 25–33 tok/s (estimate) no community data
Qwen3-8B Qwen Q8_0 Runs fully on GPU @ 8K ctx 54–73 tok/s (estimate) no community data
Qwen3-Coder-30B-A3B-Instruct Qwen Q4_K_M Runs fully on GPU @ 8K ctx no community data
Qwen3-Embedding-0.6B Qwen Q8_0 Runs fully on GPU @ 8K ctx 342–456 tok/s (estimate) no community data
Qwen3-Embedding-4B Qwen Q4_K_M Runs fully on GPU @ 8K ctx 146–194 tok/s (estimate) no community data
Qwen3-Embedding-8B Qwen Q4_K_M Runs fully on GPU @ 8K ctx 92–122 tok/s (estimate) no community data
Qwen3-Omni-30B-A3B-Instruct Qwen Q4_K_M Runs fully on GPU @ 8K ctx no community data
Qwen3-Reranker-0.6B Qwen BF16 Runs fully on GPU @ 8K ctx 253–338 tok/s (estimate) no community data
Qwen3-Reranker-4B Qwen BF16 Runs fully on GPU @ 8K ctx 58–78 tok/s (estimate) no community data
Qwen3-Reranker-8B Qwen BF16 Runs fully on GPU @ 8K ctx 31–41 tok/s (estimate) no community data
Qwen3.6-27B Qwen Q8_0 Runs fully on GPU @ 8K ctx 18–23 tok/s (estimate) no community data
Qwen3.6-35B-A3B Qwen Q4_K_M Runs fully on GPU @ 8K ctx no community data
SmolLM3-3B HuggingFaceTB BF16 Runs fully on GPU @ 8K ctx 80–106 tok/s (estimate) no community data
dots.ocr rednote-hilab BF16 Runs fully on GPU @ 8K ctx 86–114 tok/s (estimate) no community data
gemma-4-12B-it google Q8_0 Runs fully on GPU @ 8K ctx 40–53 tok/s (estimate) no community data
gemma-4-26B-A4B-it google Q8_0 Runs fully on GPU @ 8K ctx no community data
gemma-4-31B-it google Q4_K_M Runs fully on GPU @ 8K ctx 26–35 tok/s (estimate) no community data
gemma-4-E2B-it google Q8_0 Runs fully on GPU @ 8K ctx 105–141 tok/s (estimate) no community data
gemma-4-E4B-it google Q8_0 Runs fully on GPU @ 8K ctx 65–86 tok/s (estimate) no community data
gpt-oss-20b openai F16 Runs fully on GPU @ 8K ctx no community data
phi-4 microsoft Q8_0 Runs fully on GPU @ 8K ctx 31–42 tok/s (estimate) no community data
Hunyuan-A13B-Instruct tencent Q5_K_M CPU offload @ 8K ctx · ~15 GPU layers no community data
Kimi-Dev-72B moonshotai UD-Q5_K_XL CPU offload @ 8K ctx · ~39 GPU layers 1–2 tok/s (estimate) no community data
Llama-3.3-70B-Instruct meta-llama Q4_K_M CPU offload @ 8K ctx · ~51 GPU layers 2–3 tok/s (estimate) no community data

"Est. speed" is a modelled range labelled estimate (D8) for generation (decode) throughput. "Community" shows the median of approved user-submitted reports on this GPU class only where enough exist — never an estimate. "pp" is measured prompt-processing (ingestion) throughput from approved community reports; rows without a measurement show none.

What can I run on a Tesla V100 32GB?

On this GPU, 12 catalog models run fully on the GPU at an 8,192-token context. The most capable is Qwen3.6-35B-A3B at Q4_K_M (needs ~23.9 GiB). Pick a smaller model or a lower quant for more headroom.

Biggest model: Qwen3.6-35B-A3B at Q4_K_M 

llama-server -m Qwen3.6-35B-A3B-UD-Q4_K_M.gguf -c 8192 -ngl 999

Derived from the fit engine at an 8,192-token context. See more answer packs.

Add a second Tesla V100 32GB?

A second Tesla V100 32GB pools VRAM: 2 × 32 GB = 64 GB combined. Bigger models can then load because their weights split across both cards — but a second card does not make generation proportionally faster (see the reality check below).

A second Tesla V100 32GB adds 32 GB of VRAM for about $700 — ≈$21.88/GB of added VRAM (used price as of 2026-07-18 — GPU Poet).

3 more catalog models could newly fit fully in the combined 64 GB at a 8,192-token context — for example:

Estimate — assumes the model's weights split across both cards (a layer split, as llama.cpp does by default). This is a combined-VRAM projection, not a measured or verdict-chipped result: the fit engine treats two cards as one summed memory pool and does not model the link between them. Check your exact model and context in the calculator.

The honest reality of a second card

  • Bandwidth doesn't add. Two cards give more VRAM, not more memory bandwidth per token. Token generation is bandwidth-bound, so a layer-split model decodes at roughly one card's speed — not double.
  • Layer-split vs tensor-parallel. The common desktop setup (llama.cpp) splits layers across cards and runs them in sequence, so one GPU works at a time. True tensor-parallel serving (e.g. vLLM) can use both at once, but wants matched cards and a fast interconnect.
  • pp vs tg. Prompt processing (pp) can gain more from a second card than token generation (tg); raw decode throughput barely moves. Don't expect a 2× tok/s jump.
  • PCIe / NUMA. Cards talk over PCIe (or NVLink where supported), far slower than on-card VRAM. A layer split crosses it about once per token so the hit is small; tensor-parallel crosses it constantly, and cards on different CPU sockets (NUMA) add latency.
  • Power & PSU. A second card roughly doubles GPU power draw — check PSU headroom, connectors, slot spacing and airflow before buying.

Read: Multi-GPU for local LLMs — when a second card is worth it →

Derived from the fit engine at a 8,192-token context, comparing a single 32 GB card against a summed 64 GB two-card pool.

Price history

Prices are point-in-time observations, not live quotes.

used

  • Jul 2026 · $700 used — GPU Poet (medium confidence)

Not enough history yet — trends appear once at least three dated observations are recorded.

selected to compare · pick at least 2

Compare ()