Best LLMs for 32 GB
Pick your memory. We rank every catalogued model that fits at its recommended quantization, by task, and show what the next tier up unlocks.
Written by Jakub Rusinowski · Last updated
Memory tier32 GBFor example Intel Arc Pro B70, AI PRO R9700, RTX 5090
Models that fit132entirely in memory
Best at 32 GB, by task
Score is the task-specific quality score on a 0–100 scale; speed is estimated for the Intel Arc Pro B70.
CodingAll ranked →
1Qwen 2.5 Coder 32BQ4_K_M · 19.3 GB992Codestral 22BQ4_K_M · 13.4 GB973Qwen 3 32BQ4_K_M · 19.8 GB96ReasoningAll ranked →
1Llama 3.3 70B InstructQ2_K_XS (Tight) · 20.2 GB982Qwen 3 32BQ4_K_M · 19.8 GB973DeepSeek R1 Distill Qwen 32BQ4_K_M · 19.3 GB96The strongest that fit
Top 15, by logic and coding
| Model | Memory · marker = 32 GB | VRAM | Speed on Intel Arc Pro B70 (est.) | Score |
|---|---|---|---|---|
| Qwen 2.5 Coder 32B Qwen 2.5 Family · Q4_K_M | 19.3 GB | ~17 tok/s | 97 | |
| Llama 3.3 70B Instruct Llama 3.3 · Q2_K_XS (Tight) | 20.2 GB | ~16 tok/s | 97 | |
| Qwen 3 32B Qwen 3 · Q4_K_M | 19.8 GB | ~16 tok/s | 97 | |
| DeepSeek R1 Distill Qwen 32B DeepSeek R1 · Q4_K_M | 19.3 GB | ~17 tok/s | 96 | |
| Qwen 2.5 14B Instruct Qwen 2.5 Family · Q4_K_M | 8.5 GB | ~34 tok/s | 95 | |
| Qwen 3 14B Qwen 3 · Q4_K_M | 8.9 GB | ~33 tok/s | 94 | |
| Codestral 22B Codestral · Q4_K_M | 13.4 GB | ~23 tok/s | 93 | |
| Qwen 3.6 35B-A3B Qwen 3.6 · Q4_K_M | 21.1 GB | ~107 tok/s | 93 | |
| DeepSeek R1 Distill Qwen 14B DeepSeek R1 · Q4_K_M | 8.5 GB | ~34 tok/s | 92 | |
| Phi-4 (14B) Phi-4 Family · Q4_K_M | 8.5 GB | ~34 tok/s | 92 | |
| Gemma 4 31B Gemma 4 · Q4_K_M | 18.7 GB | ~17 tok/s | 92 | |
| Gemma 3 27B Instruct Gemma 3 · Q4_K_M | 16.3 GB | ~19 tok/s | 92 | |
| GLM-Z1 32B (Reasoning) GLM-4.7 / GLM-Z1 · Q4_K_M | 19.3 GB | ~17 tok/s | 92 | |
| Qwen 3.5 35B-A3B Qwen 3.5 · Q4_K_M | 21.1 GB | ~87 tok/s | 92 | |
| Mistral Small 3.1 24B Mistral Small 3.1 · Q4_K_M | 14.2 GB | ~22 tok/s | 91 |
What 48 GB unlocks
The strongest models that need the next tier up.
FAQ
What LLMs run well with 32 GB VRAM?
Qwen 2.5 Family, Llama 3.3, Qwen 3, DeepSeek R1, Qwen 2.5 Family all fit in 32 GB VRAM.
Which GPUs have 32 GB VRAM?
Intel Arc Pro B70, AMD Radeon AI PRO R9700, NVIDIA GeForce RTX 5090, Intel Arc Pro B65.
All tiers at a glance
| Memory | Models fit | Best overall | Largest that fits |
|---|---|---|---|
| 4 GB | 32 | Gemma 3 4B Instruct | Gemma 3 4B Instruct · 2.4 GB |
| 6 GB | 56 | Granite 3.0 8B Instruct | Qwen 2.5 VL 7B Instruct · 5 GB |
| 8 GB | 71 | Granite 3.0 8B Instruct | Falcon 3 10B Instruct · 6.2 GB |
| 10 GB | 83 | Qwen 2.5 14B Instruct | Qwen 3 14B · 8.9 GB |
| 12 GB | 85 | Qwen 2.5 14B Instruct | StarCoder 2 15B · 9.4 GB |
| 16 GB | 95 | Qwen 2.5 14B Instruct | Mistral Small 3 (24B) · 14.5 GB |
| 20 GB | 111 | Qwen 2.5 14B Instruct | Gemma 4 31B · 18.7 GB |
| 24 GB | 131 | Qwen 2.5 Coder 32B | Qwen 3.6 35B-A3B · 21.1 GB |
| 32 GB | 132 | Qwen 2.5 Coder 32B | Qwen 3.6 35B-A3B · 21.1 GB |
| 48 GB | 138 | Qwen 2.5 72B Instruct | Qwen 2.5 VL 72B Instruct · 44.3 GB |
| 64 GB | 143 | Qwen 2.5 72B Instruct | Qwen3-Coder-Next (80B-A3B MoE) · 48.3 GB |
| 80 GB | 152 | Qwen 2.5 72B Instruct | Qwen 3.5 122B-A10B · 73.7 GB |
Buy this hardware NVIDIA GeForce RTX 5090 32GB — 32 GB VRAM · 575 W board powerDeploy in the cloud now NVIDIA A40 on RunPod — from $0.44/hr · rate checked 2026-08
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.