RUNLOCALAIv38
→WILL IT RUNBEST GPUCOMPARETROUBLESHOOTSTARTPULSEMODELSHARDWARETOOLSBENCH
RUNLOCALAI

Independently operated catalog for local-AI hardware and software. Hand-written verdicts. Source-cited claims. Reproducible commands when we have them.

OP·Fredoline Eruo
DIR
  • Models
  • Hardware
  • Tools
  • Benchmarks
TOOLS
  • Will it run?
  • Compare hardware
  • Cost vs cloud
  • Choose my GPU
  • Quick answers
REF
  • All buyer guides
  • Methodology
  • Glossary
  • Errors KB
  • Trust
EDITOR
  • About
  • Author
  • How we make money
  • Editorial policy
  • Contact
LEGAL
  • Privacy
  • Terms
  • Sitemap
MAIL · MONTHLY DIGEST
Get monthly local AI changes
Monthly recap. No spam.
DISCLOSURE

Some links on this site are affiliate links (Amazon Associates and other first-class retailers). When you buy through them, we earn a small commission at no extra cost to you. Affiliate links do not influence our verdicts — there are cards we rate highly that we don't have affiliate relationships with, and cards that sell well that we refuse to recommend. Read more →

© 2026 runlocalai.coIndependently operated
RUNLOCALAI · v38
Will it run? / NVIDIA RTX 4090 48GB (China-mod) / chat

What can NVIDIA RTX 4090 48GB (China-mod) run for chat?

Build: NVIDIA RTX 4090 48GB (China-mod) + — + 32 GB RAM (windows)

Memory: 48 GB VRAM + 32 GB system RAM
Runner: llama.cpp / Ollama (CUDA)
AnyChatCodingAgentsReasoningVisionLong contextCreative

Runs comfortably
123 models

Ranked by fit for chat use case + predicted speed. Click a row for VRAM breakdown.

#1Llama 3.2 3B Instruct
3B
llama
Commercial OK
Quant: Q8_0Context: 8,192VRAM: 14.8 GBHeadroom: 33.2 GBTTFT: instant
ollama run llama3.2:3b
206
tok/s
E
Weights
3.19 GB
KV cache
1.50 GB
Activations
8.35 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~93 ms (instant)
Model details →Run-on benchmark page →
#2Mistral 7B Instruct v0.3
7B
mistral
Commercial OK
Quant: Q5_K_MContext: 8,192VRAM: 18.5 GBHeadroom: 29.5 GBTTFT: fast
ollama run mistral:7b
136
tok/s
E
Weights
4.81 GB
KV cache
3.50 GB
Activations
8.43 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~217 ms (fast)
Model details →Run-on benchmark page →
#3Dolphin 3.0 Llama 3.2 3B
3B
dolphin
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 13.4 GBHeadroom: 34.6 GBTTFT: instant
362
tok/s
E
Weights
1.81 GB
KV cache
1.50 GB
Activations
8.28 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~93 ms (instant)
Model details →Run-on benchmark page →
#4Qwen 3 7B
7B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.9 GBHeadroom: 30.1 GBTTFT: fast
155
tok/s
E
Weights
4.23 GB
KV cache
3.50 GB
Activations
8.40 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~217 ms (fast)
Model details →Run-on benchmark page →
#5Hermes 3 Llama 3.2 3B
3B
hermes
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 13.4 GBHeadroom: 34.6 GBTTFT: instant
362
tok/s
E
Weights
1.81 GB
KV cache
1.50 GB
Activations
8.28 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~93 ms (instant)
Model details →Run-on benchmark page →
#6Llama 3.3 8B Instruct
8B
llama
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 19.1 GBHeadroom: 28.9 GBTTFT: fast
136
tok/s
E
Weights
4.83 GB
KV cache
4.00 GB
Activations
8.43 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~248 ms (fast)
Model details →Run-on benchmark page →
#7InternLM 2.5 7B Chat
7B
internlm
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.9 GBHeadroom: 30.1 GBTTFT: fast
155
tok/s
E
Weights
4.23 GB
KV cache
3.50 GB
Activations
8.40 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~217 ms (fast)
Model details →Run-on benchmark page →
#8Falcon 3 7B Instruct
7B
falcon
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 17.9 GBHeadroom: 30.1 GBTTFT: fast
155
tok/s
E
Weights
4.23 GB
KV cache
3.50 GB
Activations
8.40 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~217 ms (fast)
Model details →Run-on benchmark page →
#9Tulu 3 8B
8B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 19.1 GBHeadroom: 28.9 GBTTFT: fast
136
tok/s
E
Weights
4.83 GB
KV cache
4.00 GB
Activations
8.43 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~248 ms (fast)
Model details →Run-on benchmark page →
#10Granite 3.0 8B Instruct
8B
granite
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 13.0 GBHeadroom: 35.0 GBTTFT: fast
136
tok/s
E
Weights
4.83 GB
KV cache
2.00 GB
Activations
4.34 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~248 ms (fast)
Model details →Run-on benchmark page →
#11Ministral 8B Instruct
8B
mistral
Quant: Q4_K_MContext: 8,192VRAM: 19.1 GBHeadroom: 28.9 GBTTFT: fast
136
tok/s
E
Weights
4.83 GB
KV cache
4.00 GB
Activations
8.43 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~248 ms (fast)
Model details →Run-on benchmark page →
#12Granite 3.0 2B Instruct
2B
granite
Commercial OK
Quant: Q4_K_MContext: 4,096VRAM: 7.7 GBHeadroom: 40.3 GBTTFT: instant
543
tok/s
E
Weights
1.21 GB
KV cache
0.50 GB
Activations
4.16 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~62 ms (instant)
Model details →Run-on benchmark page →

Runs with tradeoffs
22 models

Tight VRAM, partial CPU offload, or context-limited.

Gemma 4 31B Dense
31B
gemma
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 45.1 GBHeadroom: 2.9 GBTTFT: noticeable
  • • Tight VRAM fit — only 2.9 GB headroom left for context growth
ollama run gemma4:31b
35
tok/s
E
Weights
18.72 GB
KV cache
15.50 GB
Activations
9.13 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~961 ms (noticeable)
Model details →Run-on benchmark page →
OLMo 2 32B
32B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 46.3 GBHeadroom: 1.7 GBTTFT: noticeable
  • • Tight VRAM fit — only 1.7 GB headroom left for context growth
34
tok/s
E
Weights
19.32 GB
KV cache
16.00 GB
Activations
9.16 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~992 ms (noticeable)
Model details →Run-on benchmark page →
Tulu 3 70B
70B
other
Commercial OK
Quant: Q4_K_MContext: 2,048VRAM: 57.0 GBHeadroom: 10.2 GBTTFT: slow
  • • Partial CPU offload: ~16% of layers run on CPU
16
tok/s
E
Weights
42.26 GB
KV cache
8.75 GB
Activations
4.16 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~2169 ms (slow)
Model details →Run-on benchmark page →
Qwen 3 30B-A3B
30B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 44.0 GBHeadroom: 4.0 GBTTFT: noticeable
  • • Tight VRAM fit — only 4.0 GB headroom left for context growth
ollama run qwen3:30b
36
tok/s
E
Weights
18.11 GB
KV cache
15.00 GB
Activations
9.10 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~930 ms (noticeable)
Model details →Run-on benchmark page →
Nemotron 3 Nano (30B-A3B)
30B
other
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 44.0 GBHeadroom: 4.0 GBTTFT: noticeable
  • • Tight VRAM fit — only 4.0 GB headroom left for context growth
ollama run nemotron3:nano
36
tok/s
E
Weights
18.11 GB
KV cache
15.00 GB
Activations
9.10 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~930 ms (noticeable)
Model details →Run-on benchmark page →
Qwen 3 32B
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 46.3 GBHeadroom: 1.7 GBTTFT: noticeable
  • • Tight VRAM fit — only 1.7 GB headroom left for context growth
ollama run qwen3:32b
34
tok/s
E
Weights
19.32 GB
KV cache
16.00 GB
Activations
9.16 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~992 ms (noticeable)
Model details →Run-on benchmark page →
DeepSeek R1 Distill Qwen 32B
32B
deepseek
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 46.3 GBHeadroom: 1.7 GBTTFT: noticeable
  • • Tight VRAM fit — only 1.7 GB headroom left for context growth
ollama run deepseek-r1:32b
34
tok/s
E
Weights
19.32 GB
KV cache
16.00 GB
Activations
9.16 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~992 ms (noticeable)
Model details →Run-on benchmark page →
Qwen 2.5 32B Instruct
32B
qwen
Commercial OK
Quant: Q4_K_MContext: 8,192VRAM: 46.3 GBHeadroom: 1.7 GBTTFT: noticeable
  • • Tight VRAM fit — only 1.7 GB headroom left for context growth
ollama run qwen2.5:32b
34
tok/s
E
Weights
19.32 GB
KV cache
16.00 GB
Activations
9.16 GB
Runtime
1.80 GB
Time to first token (prefill, 512-token prompt): ~992 ms (noticeable)
Model details →Run-on benchmark page →

What if you upgraded?

Hypothetical scenarios. We re-ran the compatibility engine for each.

+32 GB system RAM

~$80–150

Doubles your CPU-offload working set. Helps when models don't quite fit in VRAM.

Unlocks: 1 new comfortable, 28 new tradeoff

  • • SmolLM 2 360M Instruct
  • • Qwen 3 30B-A3B
  • • Qwen 2.5 Coder 32B Instruct
  • • Llama 3.3 70B Instruct
Shop this upgrade↗

Upgrade to NVIDIA H100 SXM

see current pricing

80 GB VRAM (vs your 48 GB) plus a bandwidth jump from ~1008 GB/s to ~3350 GB/s.

Unlocks: 24 new comfortable

  • • QwQ 32B Preview
  • • OLMo 2 32B
  • • Codestral 22B
  • • Qwen 3 30B-A3B
Shop this upgrade↗

Add a second NVIDIA RTX 4090 48GB (China-mod)

~$2400

Tensor parallelism splits the model across both cards, effectively doubling VRAM. Bandwidth doesn't double — runs ~1.5× the single-card speed in practice.

Unlocks: 30 new comfortable

  • • QwQ 32B Preview
  • • OLMo 2 32B
  • • Codestral 22B
  • • Qwen 3 30B-A3B
Shop this upgrade↗

Some links above are affiliate links. We may earn a commission at no extra cost to you. How we make money.

Won't run
top 5 popular models

Need more memory than you have. Shown for orientation.

DeepSeek V4 Pro (1.6T MoE)
1600B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (48 GB) + 60% of system RAM (19 GB) combined.

—
Qwen 3.5 235B-A17B (MoE)
397B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (48 GB) + 60% of system RAM (19 GB) combined.

—
Qwen 3 235B-A22B
235B
qwen
Commercial OK

Even with CPU offload, needs more memory than your VRAM (48 GB) + 60% of system RAM (19 GB) combined.

—
Llama 4 Scout
109B
llama
Commercial OK

Even with CPU offload, needs more memory than your VRAM (48 GB) + 60% of system RAM (19 GB) combined.

—
DeepSeek R1 (671B reasoning)
671B
deepseek
Commercial OK

Even with CPU offload, needs more memory than your VRAM (48 GB) + 60% of system RAM (19 GB) combined.

—

How to read these numbers

M
Measured — we ran this exact combo on owner hardware.

~
Extrapolated — predicted from a measured benchmark on similar-bandwidth hardware.

E
Estimated — pure formula based on VRAM bandwidth and model architecture.

Full methodology →

Want a specific benchmark we don't have? Email support@runlocalai.co and we'll prioritize it.