24 GB · 45 models fit · data 2026-10-15

Best local LLM for 24 GB.

K2 Horizon 7B is the smartest model that fits in 24 GB. It needs about 8.6 GB and is about 36% as smart as Claude Opus 5.5.

Top picks for 24 GB, about 18 GB usable. AA = Artificial Analysis Intelligence Index; Claude Opus 5.5 = 57.6.
Model	Maker	Score (AA)	Needs 4-bit	Needs 8-bit	Run it
K2 Horizon 7B	IFM (MBZUAI)	20.6	8.6 GB	13 GB	MLX only (Mac)
Gemma 4 12B	Google	14.2	11.2 GB	16.9 GB	`ollama run gemma4:12b`
Qwen3.5 9B	Alibaba Qwen	13.3	9.6 GB	13.5 GB	`ollama run qwen3.5:9b`
Qwen3.5 4B	Alibaba Qwen	13.1	5.8 GB	8 GB	`ollama run qwen3.5:4b`
MiniCPM5 2B	OpenBMB	12.5	3.9 GB	5.1 GB	MLX only (Mac)
Granite 4.2 8B	IBM	11.1	8.1 GB	12.7 GB	`ollama run granite4.2:8b`

By job

Pick by what you do.

CodingNousCoder 14B

Needs 12.3 GB.

—

Agents (uses tools)Mellum2.1 12B-A2.5B Thinking

Needs 11.3 GB.

—

Reads imagesGemma 4 12B

Needs 11.2 GB.

ollama run gemma4:12b

New at 24 GB

What 24 GB adds over 16 GB.

Model	Needs	Score (AA)
gpt-oss-20b	15.4 GB	10
Ministral 3 14B	12.5 GB	6
Phi-4 14B	12.5 GB	5.9
Gemma 3n E4B	13.3 GB	4.8
Phi-4-reasoning-plus 14B	14.6 GB	unscored

Machines

Computers and cards with 24 GB.

Graphics cards count VRAM, so they often fit a bit more.

Prices are approximate and dated. 2026 prices are inflated by the memory-chip shortage.
Machine	Type	Usable	Models that fit	Best fit	From (approx)
MacBook Air 13"/15" (M5)	Mac laptop	18 GB	45	K2 Horizon 7B	$1,299 · 2026-10-15
MacBook Pro 14" (M5)	Mac laptop	18 GB	45	K2 Horizon 7B	$1,999 · 2026-10-15
MacBook Pro 14"/16" (M5 Pro)	Mac laptop	18 GB	45	K2 Horizon 7B	$2,499 · 2026-10-15
Mac mini (M6)	Mac desktop	18 GB	45	K2 Horizon 7B	$899 · 2026-10-15
Mac mini (M5 Pro)	Mac desktop	18 GB	45	K2 Horizon 7B	$1,699 · 2026-10-15
GeForce RTX 4090	NVIDIA graphics card	23 GB	56	Qwen3.8 27B	$3,099 · 2026-10-02
GeForce RTX 3090 (used)	NVIDIA graphics card	23 GB	56	Qwen3.8 27B	$1,430 · 2026-10-02
GeForce RTX 3090 Ti	NVIDIA graphics card	23 GB	56	Qwen3.8 27B	unknown
RTX PRO 4000 Blackwell 24GB	NVIDIA workstation card	23 GB	56	Qwen3.8 27B	$2,900 · 2026-10-15
Radeon RX 7900 XTX	AMD graphics card	23 GB	56	Qwen3.8 27B	$950 · 2026-10-02
Intel Arc Pro B60 (24GB)	Intel graphics card	23 GB	56	Qwen3.8 27B	$650 · 2026-10-15
Tesla P40 24GB (used)	Used server card	23 GB	56	Qwen3.8 27B	$277 · 2026-10-02

Questions

Short answers.

What is the best local LLM for 24 GB of RAM?: K2 Horizon 7B by IFM (MBZUAI). It scores 20.6 on the Artificial Analysis Intelligence Index and needs about 8.6 GB at 4-bit. That is about 36% of Claude Opus 5.5 (57.6), the top paid model. Data as of 2026-10-15.
How many local models fit in 24 GB?: 45 of the 124 text models in our data fit. We assume about 18 GB is usable for the model (75% of 24 GB), and a model needs its 4-bit file size × 1.15 + 2 GB.
What is the biggest model that runs in 24 GB?: gpt-oss-20b, 20.9B (3.6B active) parameters, needs about 15.4 GB at 4-bit. Bigger is not always smarter: K2 Horizon 7B scores 20.6; gpt-oss-20b scores 10.
What is the best coding model for 24 GB?: NousCoder 14B (needs 12.3 GB). Run it in a coding app like OpenCode or Cline. See https://insidethemachine.ai/best/local-coding-model.
Does 24 GB of VRAM work the same as 24 GB of RAM?: Close. On a Mac the memory is shared, and about 75% goes to the model. On a PC the graphics card's VRAM is what counts; we estimate VRAM minus 1 GB is usable, so a 24 GB card fits a little more than 24 GB of Mac memory. Models that spill out of VRAM into normal RAM run much slower.

Scores are from Artificial Analysis and LMArena, not our own tests yet. Memory need = 4-bit file × 1.15 + 2 GB; a model fits when that is at most 75% of memory. Models 2026-10-15, machines 2026-10-15.

AGENT VIEW · text/markdown · or send Accept: text/markdown

# Best local LLM for 24GB RAM or VRAM

URL: https://insidethemachine.ai/best/local-llm-for-24gb-ram
Data: models 2026-10-15, machines 2026-10-15. Source of scores: Artificial Analysis Intelligence Index (AA), LMArena. Not our own tests yet.
Usable memory assumed: 18 GB (75% of 24). Rule: min_memory_gb = weights_gb_4bit × 1.15 + 2. weights_gb_4bit = Q4_K_M file (Ollama, else HF GGUF) → MLX 4-bit (HF) → Ollama MLX/NVFP4 tag → Ollama default tag → params_total_b × 0.6 (flagged weights_estimated). +15% ≈ KV cache at ~8–16K context; +2GB runtime/process overhead. Long contexts (128K+) need much more.
Models that fit: 45 of 124.

## Top picks

| model | maker | AA index | needs (4-bit) | needs (8-bit) | run |
|---|---|---|---|---|---|
| K2 Horizon 7B | IFM (MBZUAI) | 20.6 | 8.6 GB | 13 GB | MLX only |
| Gemma 4 12B | Google | 14.2 | 11.2 GB | 16.9 GB | `ollama run gemma4:12b` |
| Qwen3.5 9B | Alibaba Qwen | 13.3 | 9.6 GB | 13.5 GB | `ollama run qwen3.5:9b` |
| Qwen3.5 4B | Alibaba Qwen | 13.1 | 5.8 GB | 8 GB | `ollama run qwen3.5:4b` |
| MiniCPM5 2B | OpenBMB | 12.5 | 3.9 GB | 5.1 GB | MLX only |
| Granite 4.2 8B | IBM | 11.1 | 8.1 GB | 12.7 GB | `ollama run granite4.2:8b` |

## By job

- Coding: NousCoder 14B (12.3 GB) 
- Agents (tool use): Mellum2.1 12B-A2.5B Thinking (11.3 GB) 
- Vision (reads images): Gemma 4 12B (11.2 GB)

## New at 24 GB (did not fit in 16 GB)

- gpt-oss-20b (15.4 GB, AA 10)
- Ministral 3 14B (12.5 GB, AA 6)
- Phi-4 14B (12.5 GB, AA 5.9)
- Gemma 3n E4B (13.3 GB, AA 4.8)
- Phi-4-reasoning-plus 14B (14.6 GB, AA unscored)

## Machines with 24 GB

| machine | type | usable GB | models that fit | best fit | from (approx) |
|---|---|---|---|---|---|
| MacBook Air 13"/15" (M5) | Mac laptop | 18 | 45 | K2 Horizon 7B | $1,299 (2026-10-15) |
| MacBook Pro 14" (M5) | Mac laptop | 18 | 45 | K2 Horizon 7B | $1,999 (2026-10-15) |
| MacBook Pro 14"/16" (M5 Pro) | Mac laptop | 18 | 45 | K2 Horizon 7B | $2,499 (2026-10-15) |
| Mac mini (M6) | Mac desktop | 18 | 45 | K2 Horizon 7B | $899 (2026-10-15) |
| Mac mini (M5 Pro) | Mac desktop | 18 | 45 | K2 Horizon 7B | $1,699 (2026-10-15) |
| GeForce RTX 4090 | NVIDIA graphics card | 23 | 56 | Qwen3.8 27B | $3,099 (2026-10-02) |
| GeForce RTX 3090 (used) | NVIDIA graphics card | 23 | 56 | Qwen3.8 27B | $1,430 (2026-10-02) |
| GeForce RTX 3090 Ti | NVIDIA graphics card | 23 | 56 | Qwen3.8 27B | unknown |
| RTX PRO 4000 Blackwell 24GB | NVIDIA workstation card | 23 | 56 | Qwen3.8 27B | $2,900 (2026-10-15) |
| Radeon RX 7900 XTX | AMD graphics card | 23 | 56 | Qwen3.8 27B | $950 (2026-10-02) |
| Intel Arc Pro B60 (24GB) | Intel graphics card | 23 | 56 | Qwen3.8 27B | $650 (2026-10-15) |
| Tesla P40 24GB (used) | Used server card | 23 | 56 | Qwen3.8 27B | $277 (2026-10-02) |

## Questions

**What is the best local LLM for 24 GB of RAM?**
K2 Horizon 7B by IFM (MBZUAI). It scores 20.6 on the Artificial Analysis Intelligence Index and needs about 8.6 GB at 4-bit. That is about 36% of Claude Opus 5.5 (57.6), the top paid model. Data as of 2026-10-15.

**How many local models fit in 24 GB?**
45 of the 124 text models in our data fit. We assume about 18 GB is usable for the model (75% of 24 GB), and a model needs its 4-bit file size × 1.15 + 2 GB.

**What is the biggest model that runs in 24 GB?**
gpt-oss-20b, 20.9B (3.6B active) parameters, needs about 15.4 GB at 4-bit. Bigger is not always smarter: K2 Horizon 7B scores 20.6; gpt-oss-20b scores 10.

**What is the best coding model for 24 GB?**
NousCoder 14B (needs 12.3 GB). Run it in a coding app like OpenCode or Cline. See https://insidethemachine.ai/best/local-coding-model.

**Does 24 GB of VRAM work the same as 24 GB of RAM?**
Close. On a Mac the memory is shared, and about 75% goes to the model. On a PC the graphics card's VRAM is what counts; we estimate VRAM minus 1 GB is usable, so a 24 GB card fits a little more than 24 GB of Mac memory. Models that spill out of VRAM into normal RAM run much slower.

More: https://insidethemachine.ai/models?tier=24 · https://insidethemachine.ai/machines?tier=24 · https://insidethemachine.ai/best