Skip to content
Run LLM Locally

Mistral Nemo 12B Instruct on the Tesla P40

With 24 GB of VRAM, the Tesla P40 runs Mistral Nemo 12B Instruct at Q4_K_M entirely on the GPU with an 8K context (about 9.4 GB needed). At Q8_0 it fits entirely.

ShareFacebookXWhatsAppLinkedInEmail

Mistral Nemo 12B Instruct

Q4_K_M · 8K context

Excellent

The model needs about 9.4 GB and fits in the 23.3 GB available, with 13.8 GB to spare.

Your hardware
Tesla P40 24 GB · 64 GB RAM
Estimated memory
~9.4 GB estimate
VRAM (usable memory)
23.3 GB
GPU only
Yes
CPU/GPU offload
Not required
Generation speed
30–41 tok/s estimate
Largest context in fast memory
92K tokens
Confidence: low

Based on: memory bandwidth (346 GB/s) and model size

Memory breakdown

~9.4 GB (9 GB–10 GB) needed · estimate

Fits entirely in VRAM · 13.8 GB left

  • Model weights7 GB
  • KV cache1.3 GB
  • Runtime overhead0.8 GB
  • Safety margin0.4 GB
Assumptions: context 8K tokens · KV cache f16 · llama.cpp (CUDA) · flash attention on · weights = real file size

EstimateData updated 24 days agoSource: Run LLM Locally engine, Hugging Face config.json + model card

What makes this estimate less reliable

  • no benchmark for this hardware and model yet

Other quantizations on the Tesla P40

Mistral Nemo 12B Instruct on Tesla P40 + 64 GB RAM · 8K context
Mistral Nemo 12B Instruct Q8_08K~14.9 GB · 19–24 tok/s estimateExcellent
Mistral Nemo 12B Instruct Q6_K8K~12 GB · 24–31 tok/s estimateExcellent
Mistral Nemo 12B Instruct Q5_K_M8K~10.7 GB · 27–35 tok/s estimateExcellent
Mistral Nemo 12B Instruct Q4_K_M8K~9.4 GB · 30–41 tok/s estimateExcellent
Mistral Nemo 12B Instruct IQ4_XS8K~8.7 GB · 33–44 tok/s estimateExcellent
Mistral Nemo 12B Instruct Q3_K_M8K~8.1 GB · 36–49 tok/s estimateExcellent

Alternatives

GPUs that run Mistral Nemo 12B Instruct Q4_K_M entirely in VRAM

Other models that fit the Tesla P40

Hardware that runs Mistral Nemo 12B Instruct Q4_K_M entirely in memory

Prices and links follow the market you choose.

GeForce RTX 2080 Ti

NVIDIA

CompatibleRuns Mistral Nemo 12B Instruct Q4_K_M entirely in memory

Price not available

Availability unknown

View on amazon.com

Affiliate link

Radeon RX 7600 XT

AMD

ExcellentRuns Mistral Nemo 12B Instruct Q4_K_M entirely in memory

Price not available

Availability unknown

View on amazon.com

Affiliate link

AMD Ryzen AI Max+ 395

Unified memory PC

ExcellentRuns Mistral Nemo 12B Instruct Q4_K_M entirely in memory

Price not available

Availability unknown

View on amazon.com

Affiliate link

GeForce RTX 3080 (10 GB)

Lowest memory tier

Compatible with limitsRuns Mistral Nemo 12B Instruct Q4_K_M entirely in memory

Price not available

Availability unknown

View on amazon.com

Affiliate link

No current offer imported for this market: the link opens a marketplace search.

Frequently asked questions

Can the Tesla P40 run Mistral Nemo 12B Instruct?
The model needs about 9.4 GB and fits in the 23.3 GB available, with 13.8 GB to spare.
Which quantization should I use on the Tesla P40?
Q8_0 is the highest-precision quantization that fits entirely in VRAM at 8K context. ~14.9 GB / 23.3 GB.
What is the largest context on the Tesla P40?
At Q4_K_M, about 92K tokens fit entirely in VRAM with an f16 KV cache. A q8_0 KV cache roughly doubles that.
How fast is Mistral Nemo 12B Instruct (Tesla P40)?
We estimate 30–41 tok/s (estimate, confidence low). Based on: memory bandwidth (346 GB/s) and model size.