Skip to content
12GB VRAM

Radeon RX 7800M — what LLMs can it run?

79 of 151 indexed models fit comfortably in 12GB at 4K context, each at the highest-quality quant that still leaves headroom.

Context length
Concurrency (batch)

The short answer for Radeon RX 7800M

12 GB, 432 GB/s GDDR6. 79 of 151 models in this index fit comfortably at 4K context; 81 load at all.

Hardware specifications source
Biggest that fits
Hy-Memory-30B-A3B — 9.9 GB at Q8_0-expsIQ2_XXS — 2.1 GB spare at 4K, so longer context comes out of a thin margin.Download: tencent/Hy-Memory-30B-A3B-GGUF · Hy-Memory-30B-A3B-Q8_0-expsIQ2_XXS.gguf · 9.14 GB · listing read 2026-11-12
Room to grow
TwIL 8B balanced — 6.3 GB at Q4_K_M — under 60% of the card, which leaves 5.7 GB for a long context window or a second process.Download: webAI-Official/TwIL-8B · TwIL-8B-Q4_K_M-balanced.gguf · 5.35 GB · listing read 2026-11-15
Speed ceiling
Llama 3.1 8B Instruct at Q4_K_M reads 4.6 GB of weights per token, so 432 GB/s puts a hard ceiling near 94 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
Laptop cooling and power limits affect performance even between laptops with the same GPU. Use the listed VRAM for fit, not desktop benchmark results for speed.
Best local LLM for 12GB

20–50B · 2

Radeon RX 7800M — what LLMs can it run? — 20–50B
ModelQuantEst. VRAMHeadroomtok/s
Hy-Memory-30B-A3B30B-A3BPair fit detailsQ8_0-expsIQ2_XXS9.95 GB+2.1 GB≤499Ceiling
Ternary Bonsai 2 27B27BPair fit detailsQ2_08.24 GB+3.8 GB≤60Ceiling

10–20B · 18

Radeon RX 7800M — what LLMs can it run? — 10–20B
ModelQuantEst. VRAMHeadroomtok/s
DeepSeek-Coder-V2-Lite Instruct16B-A2.4BQ4_K_M10.08 GB+1.9 GB≤313Ceiling
DeepSeek-V2-Lite Chat16B-A2.4BQ4_K_M10.08 GB+1.9 GB≤313Ceiling
StarCoder2 15B15BQ4_K_M9.85 GB+2.2 GB≤50Ceiling
Qwen3 14B Instruct14BQ4_K_M10.04 GB+2 GB≤51Ceiling
Qwen2.5 14B Instruct14BQ4_K_M10.14 GB+1.9 GB≤51Ceiling
DeepSeek-R1-Distill-Qwen-14B14BQ4_K_M10.14 GB+1.9 GB≤51Ceiling
Phi-4 14B14BQ4_K_M10.17 GB+1.8 GB≤51Ceiling
Phi-3 Medium 14B Instruct14BQ4_K_M9.73 GB+2.3 GB≤54Ceiling
Ministral 3 14B Instruct14BPair fit detailsQ4_K_M9.3 GB+2.7 GB≤55Ceiling
Mistral Nemo 12B Instruct12BQ4_K_M8.42 GB+3.6 GB≤61Ceiling
Gemma 3 12B IT12BQ5_K_M9.84 GB+2.2 GB≤52Ceiling
Mellum2.1 12B-A2.5B Thinking12B-A2.5BQ4_K_M8.59 GB+3.4 GB≤273Ceiling
Stable LM 2 12B Chat12BQ4_K_M8.52 GB+3.5 GB≤62Ceiling
Gemma 4 12B IT12BPair fit detailsQ4_K_M8.02 GB+4 GB≤64Ceiling
Llama 3.2 11B Vision Instruct11BQ4_K_M7.66 GB+4.3 GB≤68Ceiling
Solar 10.7B Instruct11BQ4_K_M7.6 GB+4.4 GB≤70Ceiling
Falcon 3 10B Instruct10BQ4_K_M7.28 GB+4.7 GB≤72Ceiling
Metis-1.6 Logos10B MoEPair fit detailsQ6_K9.31 GB+2.7 GB≤205Ceiling

4–10B · 37

Radeon RX 7800M — what LLMs can it run? — 4–10B
ModelQuantEst. VRAMHeadroomtok/s
Gemma 2 9B Instruct9BQ4_K_M7.3 GB+4.7 GB≤81Ceiling
Qwen3.5 9B9BPair fit detailsQ8_010.39 GB+1.6 GB≤46Ceiling
K2 Horizon 7B7BPair fit detailsQ6_K8.35 GB+3.7 GB≤61Ceiling
GLM-4-9B-Chat9BQ8_010.16 GB+1.8 GB≤48Ceiling
MiMo-V2.6-Distill-Qwen-9B9BPair fit detailsQ8_010.11 GB+1.9 GB≤48Ceiling
Clairic Flash 9B9BPair fit detailsQ8_010.1 GB+1.9 GB≤48Ceiling
Qwen3-VL 8B Instruct8BQ8_010.39 GB+1.6 GB≤49Ceiling
TwIL 8B balanced8.8BPair fit detailsQ4_K_M6.28 GB+5.7 GB≤85Ceiling
Granite 4.2 8B8BPair fit detailsQ8_010.46 GB+1.5 GB≤49Ceiling
Ministral 3 8B Instruct8BQ8_010.02 GB+2 GB≤50Ceiling
LFM2.5 8B-A1B8B-A1.5BPair fit detailsQ8_09.46 GB+2.5 GB≤285Ceiling
Qwen2-VL 7B Instruct7BQ4_K_M5.49 GB+6.5 GB≤91Ceiling
Granite 3.1 8B Instruct8BQ4_K_M5.88 GB+6.1 GB≤92Ceiling
Shot Reader 8B8BPair fit detailsQ8_09.72 GB+2.3 GB≤52Ceiling
Qwen3 8B Instruct8BQ6_K7.64 GB+4.4 GB≤68Ceiling
Llama 3.1 8B Instruct8BQ8_09.47 GB+2.5 GB≤53Ceiling
Nous Hermes 3 Llama 3.1 8B8BQ4_K_M5.64 GB+6.4 GB≤94Ceiling
Aya 23 8B8BQ4_K_M5.64 GB+6.4 GB≤94Ceiling
OpenChat 3.6 8B8BQ4_K_M5.64 GB+6.4 GB≤94Ceiling
DeepSeek-R1-Distill-Llama-8B8BQ5_K_M6.51 GB+5.5 GB≤80Ceiling
InternLM2 7B Chat7BQ4_K_M5.45 GB+6.6 GB≤97Ceiling
Qwen2.5 7B Instruct7BQ6_K6.77 GB+5.2 GB≤73Ceiling
Qwen2.5-Coder 7B Instruct7BQ4_K_M5.07 GB+6.9 GB≤98Ceiling
DeepSeek-R1-Distill-Qwen-7B7BQ4_K_M5.07 GB+6.9 GB≤98Ceiling
Gemma 4 E4B ITE4BPair fit detailsQ8_08.68 GB+3.3 GB≤55Ceiling
Nemotron 3.5 Bolt E4BE4BPair fit detailsQ8_08.5 GB+3.5 GB≤57Ceiling
OLMo 2 7B Instruct7BQ8_010.3 GB+1.7 GB≤59Ceiling
OLMo 3 7B Instruct7BQ8_010.3 GB+1.7 GB≤59Ceiling
WizardLM-2 7B7BQ4_K_M5.14 GB+6.9 GB≤104Ceiling
Mistral 7B Instruct v0.37BQ6_K6.75 GB+5.3 GB≤77Ceiling
Zephyr 7B Beta7BQ6_K6.75 GB+5.3 GB≤77Ceiling
K2 Horizon 3.7B3.7BPair fit detailsQ8_06.24 GB+5.8 GB≤85Ceiling
Gemma 4 E2B ITE2BQ8_05.2 GB+6.8 GB≤92Ceiling
Qwen3.5 4B4BQ8_04.97 GB+7 GB≤98Ceiling
Gemma 3 4B IT4BQ8_05.05 GB+7 GB≤100Ceiling
Spark-X2.6 4B4BPair fit detailsQ8_04.84 GB+7.2 GB≤104Ceiling
Qwen3 4B Instruct4BQ6_K4.05 GB+8 GB≤138Ceiling

<4B · 22

Radeon RX 7800M — what LLMs can it run? — <4B
ModelQuantEst. VRAMHeadroomtok/s
Phi-4 Mini Instruct3.8BQ8_04.81 GB+7.2 GB≤111Ceiling
Phi-3.5 Mini Instruct3.8BQ8_05.89 GB+6.1 GB≤112Ceiling
Granite 4.2 3B3BPair fit detailsQ8_04.41 GB+7.6 GB≤117Ceiling
Ministral 3 3B Instruct3BPair fit detailsQ8_04.26 GB+7.7 GB≤124Ceiling
Llama 3.2 3B Instruct3BQ8_04.05 GB+8 GB≤133Ceiling
Qwen2.5 3B Instruct3BQ8_03.59 GB+8.4 GB≤138Ceiling
SmolLM3 3B3BQ8_03.73 GB+8.3 GB≤139Ceiling
Metis-1.6 Praxis3B MoEPair fit detailsQ8_03.4 GB+8.6 GB≤382Ceiling
Gemma 2 2B Instruct2BQ8_03.34 GB+8.7 GB≤164Ceiling
Qwen3.5 2B2BQ8_02.23 GB+9.8 GB≤218Ceiling
LFM3 1.7B1.7BQ8_01.99 GB+10 GB≤247Ceiling
LFM3-VL 2B2BQ8_01.99 GB+10 GB≤247Ceiling
Qwen3 1.7B Instruct1.7BQ8_02.39 GB+9.6 GB≤248Ceiling
Qwen2.5 1.5B Instruct1.5BQ8_01.83 GB+10.2 GB≤279Ceiling
Llama 3.2 1B Instruct1BQ8_01.51 GB+10.5 GB≤346Ceiling
LFM2.5 1.2B Instruct1.2BQ8_01.35 GB+10.7 GB≤366Ceiling
K2 Horizon 0.9B0.9BQ8_01.44 GB+10.6 GB≤396Ceiling
Qwen3.5 0.8B0.8BQ8_00.94 GB+11.1 GB≤533Ceiling
BotPsy 0.8B0.75BQ8_00.9 GB+11.1 GB≤561Ceiling
Qwen2.5 0.5B Instruct0.5BQ8_00.6 GB+11.4 GB≤882Ceiling
MNN-Pocket 0.3B Instruct0.36BQ8_00.46 GB+11.5 GB≤1168Ceiling
MNN-Pocket 0.3B QAT0.30BQ4_10.26 GB+11.7 GB≤2400Ceiling

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 each estimate leaves headroom. Raise the context length and the list shortens; the calculator lets you check any combination directly. Speed figures are labelled as measurements, estimates scaled from this card's Llama 2 7B benchmark, or theoretical bandwidth ceilings.

A further 2 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.

Measured on this card

No inference runs were measured on this laptop GPU. Fit figures are estimates, not measured results.

Cards with the same budget

What fits is decided by memory, so every 12GB card of this type returns the same list. These pages are not different answers — they differ in throughput, which this index does not measure per card.

Setup guides for this card

Step-by-step guides written for the Radeon RX 7800M's runtime or memory size, with the commands and the checks that prove the model is running on the card.

Stepping up

A Radeon RX 9070 XT (16GB) fits 8 more of the indexed models than this card. Radeon RX 9070 XT →

Common questions

What is the best local LLM for a Radeon RX 7800M?

For everyday use, TwIL 8B balanced at Q4_K_M — about 6.3 GB of the card's 12 GB at 4K context, leaving 5.7 GB for a longer window. If you want the largest thing that will load, that is Hy-Memory-30B-A3B at Q8_0-expsIQ2_XXS (9.9 GB, 2.1 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 Radeon RX 7800M run North Mini Code 1.0 30B-A3B?

No. Its smallest build here, Q3_K_M, needs about 15.3 GB and this card has 12.0 GB usable — short by 3.3 GB before any context beyond 4K. The largest model this card does clear is Hy-Memory-30B-A3B.

How many tokens per second does a Radeon RX 7800M 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 432 GB/s — a ceiling near 94 tok/s. Batch size, context length, the runtime and how much of the model sits in cache all take you below it.

Radeon RX 7800M or RTX 3080 Ti for local LLMs?

They hold the same models: 12 GB against 12 GB fits 79 and 79 of 151 respectively at 4K. The difference is throughput — 432 GB/s against 912 GB/s, a 2.1× gap in how fast the weights can be read, which is what token generation is bound by. The RTX 3080 Ti generates faster on any model both can hold.

79 of 151 indexed models fit comfortably in 12GB at 4K context, each at the highest-quality quant that still leaves headroom.

This page's figures change when the model or the runtime does.Last updated 2026-11-22 RSS → /feed.xml