Best LLMs for 8 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 tier8 GBFor example RTX 5050, RTX 5060, RTX 4060
Models that fit71entirely in memory
Best at 8 GB, by task
Score is the task-specific quality score on a 0–100 scale; speed is estimated for the RTX 5050.
CodingAll ranked →
1Granite 3.0 8B InstructQ4_K_M · 4.8 GB922Qwen 2.5 7B InstructQ4_K_M · 4.6 GB903Ternary Bonsai 27BTernary (1.58-bit, ~1.71 bpw) · 5.8 GB89ReasoningAll ranked →
1DeepSeek R1 Distill Llama 8BQ4_K_M · 4.8 GB922Ternary Bonsai 27BTernary (1.58-bit, ~1.71 bpw) · 5.8 GB903Qwen 3 8BQ4_K_M · 5 GB90ChatAll ranked →
1Gemma 2 9B ITQ4_K_M · 5.4 GB952Llama 3.1 8B InstructQ4_K_M · 4.8 GB853GLM-4 9BQ4_K_M · 5.4 GB84The strongest that fit
Top 15, by logic and coding
| Model | Memory · marker = 8 GB | VRAM | Speed on RTX 5050 (est.) | Score |
|---|---|---|---|---|
| Granite 3.0 8B Instruct Granite 3.0 · Q4_K_M | 4.8 GB | ~45 tok/s | 90 | |
| Ternary Bonsai 27B Bonsai 27B · Ternary (1.58-bit, ~1.71 bpw) | 5.8 GB | ~37 tok/s | 90 | |
| Qwen 2.5 7B Instruct Qwen 2.5 Family · Q4_K_M | 4.6 GB | ~50 tok/s | 89 | |
| Qwen 3 8B Qwen 3 · Q4_K_M | 5 GB | ~44 tok/s | 89 | |
| DeepSeek R1 Distill Llama 8B DeepSeek R1 · Q4_K_M | 4.8 GB | ~46 tok/s | 89 | |
| InternLM 3 8B Instruct InternLM 3 · Q4_K_M | 5.3 GB | ~44 tok/s | 86 | |
| Qwen 3.5 9B Qwen 3.5 · Q4_K_M | 5.4 GB | ~44 tok/s | 86 | |
| 1-bit Bonsai 27B Bonsai 27B · 1-bit (binary, ~1.125 bpw) | 3.8 GB | ~52 tok/s | 86 | |
| Yi 1.5 9B Chat Yi 1.5 Family · Q4_K_M | 5.3 GB | ~43 tok/s | 85 | |
| Falcon 3 10B Instruct Falcon 3 · Q4_K_M | 6.2 GB | ~36 tok/s | 85 | |
| GLM-4 9B GLM-4.7 / GLM-Z1 · Q4_K_M | 5.4 GB | ~41 tok/s | 85 | |
| Gemma 2 9B IT Gemma 2 Family · Q4_K_M | 5.4 GB | ~36 tok/s | 84 | |
| Llama 3.1 8B Instruct Llama 3.1 Family · Q4_K_M | 4.8 GB | ~46 tok/s | 83 | |
| Granite 4.1 8B IBM Granite 4.1 · Q4_K_M | 4.8 GB | ~45 tok/s | 83 | |
| EXAONE 3.5 7.8B EXAONE 3.5 · Q4_K_M | 4.7 GB | ~46 tok/s | 82 |
What 10 GB unlocks
The strongest models that need the next tier up.
FAQ
What LLMs run well with 8 GB VRAM?
Granite 3.0, Bonsai 27B, Qwen 2.5 Family, Qwen 3, DeepSeek R1 all fit in 8 GB VRAM.
Which GPUs have 8 GB VRAM?
NVIDIA GeForce RTX 5050, NVIDIA GeForce RTX 5060, NVIDIA GeForce RTX 4060, AMD Radeon RX 9060 XT 8GB.
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 Intel Arc B570 10GB — 10 GB VRAM · 150 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.
Can-I-Run Pages Near 8 GB
- BitNet b1.58 on NVIDIA GeForce RTX 5060 Ti 8GB
- BitNet b1.58 on NVIDIA GeForce RTX 5060
- BitNet b1.58 on NVIDIA GeForce RTX 4060
- DeepSeek R1 on NVIDIA GeForce RTX 5060 Ti 8GB
- DeepSeek R1 on NVIDIA GeForce RTX 5060
- DeepSeek R1 on NVIDIA GeForce RTX 4060
- DeepSeek R1 on NVIDIA GeForce RTX 3070 Ti
- DeepSeek R1 on NVIDIA GeForce RTX 3070