← All guides
Hardware July 22, 2026

Best Local LLM for 48GB VRAM or RAM (2026): Qwen 3.6 27B Q8

48GB is a solid tier in July 2026. Qwen 3.6 27B at Q8 remains the best overall pick. New this month: Poolside's Laguna XS 2.1 (33B/3B MoE, 256K context) fits at about 36GB at Q8 and is the best agentic coding model you can run at this tier — cap the context to keep it inside 48GB. Note: Llama 4 Scout needs ~58-60GB and does NOT fit 48GB — you need 64GB for Scout.

Running 8-hour OpenClaw agents on M3 Max?

See our AI training options. We'll dial in dual-model routing + context strategy + launchd for unattended overnight runs.

Apple Mac for 48GB RAM local AI on Amazon
🛒 BEST MAC FOR 48GB RAM Apple MacBook Pro · 48GB+ unified memory 48GB unified memory runs 70B-class models and multi-model setups — the recommended Mac for serious local AI. Check current price on Amazon →
Updated July 22, 2026 — Laguna XS 2.1 reaches this tier
  • Laguna XS 2.1 (Poolside, 33B/3B MoE) — ~36GB at Q8, 256K context, best agentic coding at 48GB; cap the context or use INT4 weights
  • Gemma 4 26B-A4B (Google, June 3) — 26B MoE, ~15GB at Q4, 45-65 tok/sec, best fast secondary model
  • Devstral Small 24B (Mistral) — dedicated coding model, ~14.5GB at Q4, strong HumanEval
  • Llama 4 Scout (10M context) needs ~58GB — does not fit 48GB. Need 64GB for Scout.

Shopping, not just reading? Our full gear ladder lists every verified pick by tier — Macs, single GPUs, and multi-GPU builds — with what to buy and what to skip.

Bottom Line (2026)

  • Best overall pick: Qwen 3.6 27B at Q8_0 (near-FP16 quality, 30GB footprint)
  • Best agentic coding: Laguna XS 2.1 (33B/3B MoE) at Q8 — ~36GB, 256K context, in Ollama
  • Best for fast inference: Qwen 3.6 35B-A3B MoE at Q6_K (40-60 tok/sec)
  • Best for OpenClaw production: Dual — gpt-oss 20B Q8 + Qwen 3.6 27B Q5
  • Best new lightweight model: Gemma 4 26B-A4B — ~15GB, 45-65 tok/sec, great second model
  • Best dense multimodal pick: Gemma 4 31B at Q8_0 (~32.6GB) — 30.7B params, 256K context, reads images
  • Best small coding model: Devstral Small 24B — fits at 14.5GB, leaves room for a second model

Top Picks for 48GB RAM

1. Qwen 3.6 27B (Q8_0) — best general-purpose at premium quality

Q8_0 of the April 22 release uses about 30GB and gives near-FP16 quality. The “ship it forever” pick at this tier. Speed: 25-40 tok/sec on M3 Max.

ollama pull qwen3.6:27b-q8_0
openclaw config set agents.defaults.models.chat ollama/qwen3.6:27b-q8_0

2. Laguna XS 2.1 (33B/3B MoE) at Q8 — best agentic coding [New July 2026]

Poolside’s July 2026 agentic coding model. 33B total parameters with 3B active per token (MoE), a 256K context window, and up to 32K output tokens. At Q8/FP8 the weights use about 33-36GB. It gains +5.4% on SWE-bench Multilingual over Laguna XS.2 and is built for tool calling and long terminal runs.

48GB is the tight end for this model. After macOS overhead you have about 38-40GB, so the Q8 weights leave only a few GB for the KV cache. Cap the context at 32-64K, or pull the INT4/NVFP4 weights if you need the full 256K window.

ollama pull laguna-xs-2.1
openclaw config set agents.defaults.models.agent ollama/laguna-xs-2.1
openclaw config set agents.defaults.context 65536
openclaw run --agent "Fix the failing tests and open a PR"

Weights ship in BF16, FP8, NVFP4, and INT4 on Hugging Face. The FP8 KV cache keeps memory flat during long agent loops, which matters more at 48GB than at 64GB.

3. Qwen 3.6 35B-A3B (Q6_K) — fastest at this tier

The Mixture-of-Experts variant of Qwen 3.6 at Q6_K uses about 30GB. 35B total parameters with 3B active per token = 8B-class inference speed with 35B-class knowledge. The right pick if you do many short interactions.

ollama pull qwen3.6:35b-q6_K
openclaw config set agents.defaults.models.chat ollama/qwen3.6:35b-q6_K

4. Dual-Model OpenClaw Setup (the 48GB advantage)

Keep two specialized models loaded for instant routing:

# gpt-oss 20B Q8 for autonomous agent runs (cleanest tool calls) — 22GB
# Qwen 3.6 27B Q5 for general chat (premium reasoning) — 20GB

openclaw config set agents.defaults.models.chat ollama/qwen3.6:27b-q5_K_M
openclaw config set agents.defaults.models.agent ollama/gpt-oss:20b-q8_0
openclaw config set agents.defaults.keep_alive 30m

# Verify
openclaw models status

This routing pattern is unique to 48GB+ tiers. Below this, model swap latency hurts.

5. Nemotron Cascade 2 30B (Q8_0) — premium structured output

NVIDIA’s late-March 2026 release at Q8 uses about 32GB. Strongest open model for JSON output and structured generation at this RAM tier.

ollama pull nemotron-cascade-2:30b-q8_0

6. Mistral Small 4 (119B-A6B MoE, IQ3_XS) — squeeze for the new Mistral

Mistral’s March 16, 2026 release replaces Mistral Large 123B. The 119B-A6B MoE at IQ3_XS uses about 38GB. 6B active params per token = fast inference. Quality is degraded at IQ3 but still useful.

ollama pull mistral-small-4:iq3_xs

What Fits in 48GB

ModelQuantRAM UsedTool Calling
Qwen 3.6 27BQ8_0~33 GBExcellent
Qwen 3.6 35B-A3BQ6_K~33 GBExcellent
Laguna XS 2.1 33B-A3BQ8/FP8~36 GB (cap context)Excellent
Gemma 4 31B (dense, 256K ctx)Q8_0~32.6 GBGood
Nemotron Cascade 2 30BQ8_0~34 GBGood
Mistral Small 4 119B-A6BIQ3_XS~40 GBGood
Qwen 3.5 122B-A10BIQ3_XS~42 GBFair (Ollama bug)
gpt-oss 20B + Qwen 3.6 27B Q5 (dual)Q8 + Q5~42 GBExcellent

Common Mistakes at 48GB

  1. Defaulting to Llama 3.3 70B at Q3 because “bigger is better”. Qwen 3.6 27B at Q8 now outperforms Llama 3.3 70B Q4 on most agentic tasks.
  2. Running Q8 of a 27B with 256K context. KV cache eats 30GB+ on top of the model. Cap at 64K for Q8.
  3. Forgetting the OS uses RAM too. macOS Sonoma/Sequoia uses 6-10GB during normal use. Treat 48GB as 38-40GB available.
  4. Running Laguna XS 2.1 at Q8 with the full 256K context. The weights already take ~36GB. The KV cache then pushes you into swap. Cap the context at 32-64K, or use the INT4 weights.
  5. Picking Qwen 3.5 122B-A10B for OpenClaw. Tool calling bug affects this MoE too. Use Qwen 3.6 27B/35B-A3B instead.

🛒 Recommended hardware for local AI

The two Macs that handle the workloads on this page.

Amazon affiliate links — we earn a small commission at no cost to you.

Hardware That Actually Hits 48GB

  • M3 Max MacBook Pro (48GB) — best laptop pick
  • M4 Max MacBook Pro (48GB)
  • Mac Studio M2 Max (64GB) — close enough, gives headroom
  • NVIDIA RTX A6000 48GB — workstation, single card
  • 2x RTX 3090 24GB — 48GB total VRAM (Linux setup, complex)

FAQ

What is the best local LLM for 48GB RAM in 2026?

Qwen 3.6 27B at Q8_0 (~30GB) is the best general-purpose pick — near-FP16 quality, 77.2% SWE-Bench. For agentic coding, Poolside Laguna XS 2.1 (33B/3B MoE, 256K context) uses about 36GB at Q8 and is the strongest coding model that fits this tier. Gemma 4 26B-A4B MoE (~15GB Q4) is the best fast second model. For OpenClaw production, gpt-oss 20B Q8 + Qwen 3.6 27B Q5 dual setup is the strongest combination.

Can I run Laguna XS 2.1 on 48GB RAM?

Yes, but keep the context capped. Laguna XS 2.1 is Poolside's 2026 agentic coding model: 33B total parameters with 3B active per token (MoE), a 256K context window, and up to 32K output tokens. At Q8/FP8 the weights use about 33-36GB. On 48GB you have roughly 38-40GB free after macOS, so run it at 32-64K context, or use the INT4/NVFP4 weights for full-context headroom. It gains +5.4% on SWE-bench Multilingual over Laguna XS.2 and is in the Ollama library.

Does Llama 4 Scout fit in 48GB RAM?

No. Llama 4 Scout (109B/17B MoE) at Q4 uses approximately 58-60GB — it does NOT fit in 48GB unified memory. After macOS overhead (~15GB), you only have ~33GB free at 48GB. You need 64GB for Scout. For the 10M context window, upgrade to the 64GB tier.

Can I run Qwen 3.6 35B-A3B on 48GB?

Yes, comfortably at Q6_K (~30GB) or Q8_0 (~38GB). The MoE design means inference is roughly 8B-class speed (40-60 tokens per second on Apple Silicon) with 35B-class knowledge. This is the best fast model at the 48GB tier.

What is Gemma 4 26B-A4B and does it run locally?

Gemma 4 26B-A4B is Google's June 3, 2026 MoE release. 26B total parameters, ~4B active per token. At Q4_K_M it uses about 15GB and runs at 45-65 tok/sec on Apple Silicon. Apache 2.0 license. It fits easily at any RAM tier above 24GB and is an excellent fast second model in dual-model setups. If you want the dense Gemma instead, Gemma 4 31B (30.7B parameters, 256K context, multimodal) runs at Q8_0 in about 32.6GB, which 48GB accommodates with context headroom.

What is the best LLM for 48GB VRAM?

On a 48GB card such as the RTX A6000, or two RTX 3090s, run Qwen 3.6 27B at Q8_0 (~30GB) for quality or Laguna XS 2.1 at Q8 (~33-36GB) for coding. Llama 3.3 70B fits at Q4 (~42GB) with about 19K tokens of context left. See the 48GB VRAM setup guide and the RTX A6000 guide.

Which local LLM is best for OpenClaw on 48GB?

Run the dual setup: gpt-oss 20B at Q8_0 (~22GB) as the agent model and Qwen 3.6 27B at Q5_K_M (~20GB) as the chat model, both resident at once. gpt-oss 20B has the cleanest tool-call JSON of any open-weight model. Set keep_alive to 30m and check with openclaw models status.

What is the best local LLM for Swift coding on 48GB?

Laguna XS 2.1 at Q8 (~36GB), the strongest agentic coding model at this tier with 70.9% on SWE-bench Verified. Devstral Small 24B at Q4_K_M (~14.5GB) is the small alternative that leaves room for a second model. Neither is Swift-specific. Cap the context at 32-64K on 48GB.

Before you order parts, check the tested hardware list for current prices by tier.

See Also

Need OpenClaw fixed live?

Remote rescue sessions for gateway, auth, tunnel, VPS, and model access problems.

See Rescue Session

Read next

Best Local LLM for 64GB RAM (2026): gpt-oss 120B Wins
Best local LLMs for 64GB RAM in 2026. Llama 4 Scout (10M context, ~58GB Q4), gpt-oss 120B at Q4, DeepSeek V4 Flash (284B MoE, Ollama cloud), Laguna XS 2.1 (agentic coding, 33B-A3B, ~36GB Q8). Also: Mistral Small 4, Qwen 3.6 35B Q8.
Best Local LLM for 32GB RAM (2026): Qwen 3.6 27B Wins
The best local LLM for 32GB RAM is Qwen 3.6 27B at Q6_K, about 22GB in use. Tested picks with tok/sec, exact Ollama commands, and what to avoid on 32GB.
Best Local LLMs for 24GB RAM (2026): Qwen 3.6 27B Headlines
Best local LLMs for 24GB RAM in 2026. Qwen 3.6 27B (released Apr 22) is the new headline pick — outperforms 397B MoE models on agentic coding. Plus gpt-oss 20B, Qwen 3.5 9B at Q8.
Best Local LLM for 96GB RAM (2026): gpt-oss 120B at Q5
Best local LLMs for 96GB RAM in 2026. Llama 4 Scout (10M context, ~58GB Q4), DeepSeek V4 Flash (~80GB Q4), gpt-oss 120B at Q5 (~80GB), Qwen 3.5 122B-A10B, Mistral Small 4 at Q5. Mac Studio M3 Ultra territory.