24GB VRAM

Tesla P40 24G — what LLMs can it run?

65 of 81 indexed models fit comfortably in 24GB at 4K context, each at the highest-quality quant that still leaves headroom.

The short answer for Tesla P40 24G

24 GB, 346 GB/s GDDR5. 65 of 81 models in this index fit comfortably at 4K context; 66 load at all.

Biggest that fits: Seed-OSS 36B Instruct — 19.9 GB at AWQ INT4 — 4.1 GB spare at 4K, so longer context comes out of a thin margin.
Room to grow: GPT-OSS 20B — 11.8 GB at MXFP4 — under 60% of the card, which leaves 12.2 GB for a long context window or a second process.
Speed ceiling: Llama 3.1 8B Instruct at Q4_K_M reads 4.6 GB of weights per token, so 346 GB/s puts a hard ceiling near 75 tok/s. That is arithmetic on two published numbers, not a benchmark — real throughput lands below it. No run on this card has been measured here, so there is nothing to compare the ceiling against.
The wall you will hit: Bandwidth, not capacity. The models on this page fit, but at 346 GB/s this card reads the whole weight set once per generated token — a 1,008 GB/s RTX 4090 holds exactly the same 24 GB and moves those bytes 2.9× faster. Expect the same quant to generate proportionally slower here.

Best local LLM for 24GB

32B · 18

Tesla P40 24G — what LLMs can it run? — 32B
Model	Quant	Est. VRAM	Headroom	tok/s
Seed-OSS 36B Instruct36B	AWQ INT4	19.91 GB	+4.1 GB	55
Command R 35B35B	GPTQ INT4	18.97 GB	+5 GB	55
Yi 1.5 34B Chat34B	AWQ INT4	19 GB	+5 GB	52
Qwen3 32B Instruct32B	AWQ INT4	18.22 GB	+5.8 GB	55
Qwen2.5 32B Instruct32B	EXL2 3.5bpw	15.96 GB	+8 GB	68
Qwen2.5-Coder 32B Instruct32B	AWQ INT4	18.08 GB	+5.9 GB	52
DeepSeek-R1-Distill-Qwen-32B32B	EXL2 3.5bpw	15.96 GB	+8 GB	65
Qwen3 30B-A3B Instruct30B-A3B	Q4_K_M	19.73 GB	+4.3 GB	95
Qwen3-Coder 30B-A3B Instruct30B-A3B	Q4_K_M	19.73 GB	+4.3 GB	92
Qwen3-VL 30B-A3B Instruct30B-A3B	Q4_K_M	19.73 GB	+4.3 GB	95
Qwen3.8 27B27B	Q4_K_M	17.47 GB	+6.5 GB	—
Gemma 3 27B IT27B	Q4_K_M	19.49 GB	+4.5 GB	48
Gemma 2 27B Instruct27B	Q4_K_M	18.81 GB	+5.2 GB	48
Mistral Small 24B Instruct24B	EXL2 4.65bpw	15.26 GB	+8.7 GB	88
Devstral Small 1.1 24B24B	Q6_K	20.91 GB	+3.1 GB	48
Magistral Small 1.2 24B24B	Q6_K	20.91 GB	+3.1 GB	47
Codestral 22B22B	Q4_K_M	15.03 GB	+9 GB	58
GPT-OSS 20B21B MoE	MXFP4	11.81 GB	+12.2 GB	195

14B · 17

Tesla P40 24G — what LLMs can it run? — 14B
Model	Quant	Est. VRAM	Headroom	tok/s
InternLM2 20B Chat20B	Q5_K_M	15.59 GB	+8.4 GB	68
DeepSeek-Coder-V2-Lite Instruct16B	Q8_0	18.36 GB	+5.6 GB	118
DeepSeek-V2-Lite Chat16B	Q4_K_M	10.87 GB	+13.1 GB	142
StarCoder2 15B15B	Q4_K_M	10.19 GB	+13.8 GB	92
Qwen3 14B Instruct14B	Q5_K_M	11.65 GB	+12.4 GB	78
Qwen2.5 14B Instruct14B	Q5_K_M	11.73 GB	+12.3 GB	86
DeepSeek-R1-Distill-Qwen-14B14B	EXL2 4.65bpw	9.75 GB	+14.3 GB	128
Phi-4 14B14B	Q5_K_M	11.77 GB	+12.2 GB	78
Phi-3 Medium 14B Instruct14B	Q6_K	12.86 GB	+11.1 GB	88
Mistral Nemo 12B Instruct12B	Q6_K	11.14 GB	+12.9 GB	95
Gemma 3 12B IT12B	Q5_K_M	10.6 GB	+13.4 GB	92
Stable LM 2 12B Chat12B	Q4_K_M	8.35 GB	+15.7 GB	108
Jamba 1.5 Mini12B	Q4_K_M	8.15 GB	+15.9 GB	95
Llama 3.2 11B Vision Instruct11B	Q8_0	12.9 GB	+11.1 GB	72
Solar 10.7B Instruct11B	Q4_K_M	7.6 GB	+16.4 GB	125
Falcon 3 10B Instruct10B	Q4_K_M	7.28 GB	+16.7 GB	118
Gemma 2 9B Instruct9B	Q8_0	11.7 GB	+12.3 GB	108

7B · 20

Tesla P40 24G — what LLMs can it run? — 7B
Model	Quant	Est. VRAM	Headroom	tok/s
GLM-4-9B-Chat9B	Q8_0	10.16 GB	+13.8 GB	105
Qwen3-VL 8B Instruct8B	Q8_0	10.39 GB	+13.6 GB	108
Ministral 3 8B Instruct8B	Q8_0	10.02 GB	+14 GB	—
Qwen2-VL 7B Instruct7B	Q4_K_M	5.49 GB	+18.5 GB	72
Granite 3.1 8B Instruct8B	Q4_K_M	5.88 GB	+18.1 GB	142
Qwen3 8B Instruct8B	Q6_K	7.64 GB	+16.4 GB	122
Llama 3.1 8B Instruct8B	Q8_0	9.47 GB	+14.5 GB	118
Nous Hermes 3 Llama 3.1 8B8B	EXL2 4.65bpw	5.43 GB	+18.6 GB	232
Aya 23 8B8B	Q4_K_M	5.64 GB	+18.4 GB	145
OpenChat 3.6 8B8B	EXL2 4.65bpw	5.43 GB	+18.6 GB	228
DeepSeek-R1-Distill-Llama-8B8B	Q5_K_M	6.51 GB	+17.5 GB	128
InternLM2 7B Chat7B	Q4_K_M	5.45 GB	+18.6 GB	148
Qwen2.5 7B Instruct7B	Q6_K	6.77 GB	+17.2 GB	132
Qwen2.5-Coder 7B Instruct7B	EXL2 4.65bpw	4.87 GB	+19.1 GB	248
WizardLM-2 7B7B	Q4_K_M	5.07 GB	+18.9 GB	152
DeepSeek-R1-Distill-Qwen-7B7B	EXL2 4.65bpw	4.87 GB	+19.1 GB	210
OLMo 2 7B Instruct7B	Q8_0	10.3 GB	+13.7 GB	125
Mistral 7B Instruct v0.37B	Q6_K	6.75 GB	+17.3 GB	135
Zephyr 7B Beta7B	Q6_K	6.75 GB	+17.3 GB	132
Gemma 3 4B IT4B	Q8_0	5.36 GB	+18.6 GB	145

≤3B · 10

Tesla P40 24G — what LLMs can it run? — ≤3B
Model	Quant	Est. VRAM	Headroom	tok/s
Qwen3 4B Instruct4B	Q6_K	4.05 GB	+20 GB	145
Phi-4 Mini Instruct3.8B	Q8_0	4.68 GB	+19.3 GB	262
Phi-3.5 Mini Instruct3.8B	Q8_0	5.89 GB	+18.1 GB	255
Llama 3.2 3B Instruct3B	Q8_0	4.05 GB	+20 GB	285
Qwen2.5 3B Instruct3B	Q8_0	3.67 GB	+20.3 GB	290
Gemma 2 2B Instruct2B	Q8_0	3.34 GB	+20.7 GB	320
Qwen3 1.7B Instruct1.7B	Q8_0	2.39 GB	+21.6 GB	240
Qwen2.5 1.5B Instruct1.5B	Q8_0	1.83 GB	+22.2 GB	410
Llama 3.2 1B Instruct1B	Q8_0	1.51 GB	+22.5 GB	450
Qwen2.5 0.5B Instruct0.5B	Q8_0	0.6 GB	+23.4 GB	540

How this list is built

Each row is the lowest-perplexity-loss quant of that model whose estimated total — weights plus KV cache at 4K context plus activation buffer — uses at most 88% of the card. That is the calculator's "green" threshold, so every row here has real headroom rather than only just fitting. Raise the context length and the list shortens; the calculator lets you check any combination directly.

A further 1 models load but with no headroom to spare (up to 105% of VRAM) — the Quant Hub’s GPU chips count those too, which is why its number is higher.

Open this card in the VRAM calculator Browse all 81 models

Measured on this card

No benchmark runs in this index were recorded on a Tesla P40 24G. Every figure on this page is calculated from the model architecture and the quant level — treat them as estimates, not measurements.

Stepping up

A A100 40G (40GB) fits 3 more of the indexed models than this card. A100 40G →

Common questions

What is the best local LLM for a Tesla P40 24G?

For everyday use, GPT-OSS 20B at MXFP4 — about 11.8 GB of the card's 24 GB at 4K context, leaving 12.2 GB for a longer window. If you want the largest thing that will load, that is Seed-OSS 36B Instruct at AWQ INT4 (19.9 GB, 4.1 GB spare). "Best" here means best fit for the memory budget — this index does not run task benchmarks, so it cannot tell you which model is smarter.

Can a Tesla P40 24G run Mixtral 8x7B Instruct?

Only just. Its smallest build here, AWQ INT4, needs about 24.9 GB against 24 GB — that loads on a card with nothing else on it, with no margin for a longer context window. It is not on the list above, which requires a model to stay inside 88% of the card.

How many tokens per second does a Tesla P40 24G do on an 8B model at Q4?

This index has no measured run on this card, so it does not publish a figure. What can be stated from specifications: generating a token requires reading every weight once, Llama 3.1 8B Instruct at Q4_K_M is 4.6 GB of weights, and this card moves 346 GB/s — a ceiling near 75 tok/s. Batch size, context length, the runtime and how much of the model sits in cache all take you below it.

Tesla P40 24G or RTX 4090 for local LLMs?

They hold the same models: 24 GB against 24 GB fits 65 and 65 of 81 respectively at 4K. The difference is throughput — 346 GB/s against 1,008 GB/s, a 2.9× gap in how fast the weights can be read, which is what token generation is bound by. The RTX 4090 generates faster on any model both can hold.

This page's figures change when the model or the runtime does.Last updated 2026-09-14 RSS → /feed.xml