Best LLMs for 20 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 tier20 GBFor example RX 7900 XT, RX 7900 XTX, RTX 3090
Models that fit111entirely in memory
Best at 20 GB, by task
Score is the task-specific quality score on a 0–100 scale; speed is estimated for the RX 7900 XT.
CodingAll ranked →
1Codestral 22BQ4_K_M · 13.4 GB972Qwen 3 14BQ4_K_M · 8.9 GB933Granite 3.0 8B InstructQ4_K_M · 4.8 GB92ReasoningAll ranked →
1Qwen 3 14BQ4_K_M · 8.9 GB942DeepSeek R1 Distill Qwen 14BQ4_K_M · 8.5 GB943Phi-4 (14B)Q4_K_M · 8.5 GB94The strongest that fit
Top 15, by logic and coding
| Model | Memory · marker = 20 GB | VRAM | Speed on RX 7900 XT (est.) | Score |
|---|---|---|---|---|
| Qwen 2.5 14B Instruct Qwen 2.5 Family · Q4_K_M | 8.5 GB | ~47 tok/s | 95 | |
| Qwen 3 14B Qwen 3 · Q4_K_M | 8.9 GB | ~46 tok/s | 94 | |
| Codestral 22B Codestral · Q4_K_M | 13.4 GB | ~32 tok/s | 93 | |
| DeepSeek R1 Distill Qwen 14B DeepSeek R1 · Q4_K_M | 8.5 GB | ~48 tok/s | 92 | |
| Phi-4 (14B) Phi-4 Family · Q4_K_M | 8.5 GB | ~47 tok/s | 92 | |
| Gemma 4 31B Gemma 4 · Q4_K_M | 18.7 GB | — | 92 | |
| Gemma 3 27B Instruct Gemma 3 · Q4_K_M | 16.3 GB | ~27 tok/s | 92 | |
| Mistral Small 3.1 24B Mistral Small 3.1 · Q4_K_M | 14.2 GB | ~31 tok/s | 91 | |
| Qwen 3.6 27B Qwen 3.6 · Q4_K_M | 16.8 GB | ~27 tok/s | 91 | |
| InternLM 3 20B Instruct InternLM 3 · Q4_K_M | 12.1 GB | ~35 tok/s | 91 | |
| Qwen3.8 27B Qwen3.8 · Q4_K_M | 16.8 GB | ~27 tok/s | 91 | |
| Mistral Small 3 (24B) Mistral Family · Q4_K_M | 14.5 GB | ~30 tok/s | 90 | |
| Qwen 3 30B-A3B (MoE) Qwen 3 · Q4_K_M | 18.4 GB | ~123 tok/s | 90 | |
| Granite 3.0 8B Instruct Granite 3.0 · Q4_K_M | 4.8 GB | ~71 tok/s | 90 | |
| GLM-4.7-Flash 30B-A3B GLM-4.7 / GLM-Z1 · Q4_K_M | 18.1 GB | ~115 tok/s | 90 |
What 24 GB unlocks
The strongest models that need the next tier up.
FAQ
What LLMs run well with 20 GB VRAM?
Qwen 2.5 Family, Qwen 3, Codestral, DeepSeek R1, Phi-4 Family all fit in 20 GB VRAM.
Which GPUs have 20 GB VRAM?
AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 4090.
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 AMD Radeon RX 7900 XT 20GB — 20 GB VRAM · 315 W board powerDeploy in the cloud now RTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07
or compare on Vast.ai from $0.35/hr (typical low · varies)
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.