FitMyLLM
AMD· GCN 1.0

AMD Radeon R9 370

Running LLMs on the Radeon R9 370 — the long read: which models fit at which quantisation, and the settings worth changing. · Or what a budget buys

VRAM
2 GB
Budget
Bandwidth
179
GB/s
Models Q4
48/498
10%
7B Q4 speed
~23
Good
Model coverage at Q410% of all
Estimated speed· By model size at Q4

Average speeds at Q4 quantization. Actual performance varies by model architecture and context length.

3B
—
1.7GB needed
7B
—
3.9GB needed
14B
—
7.9GB needed
32B
—
18.0GB needed
70B
—
39.4GB needed
Measured rig reports

We rent the machine and time every model on it: decode, VRAM peak, concurrency, watts and cost per million tokens. Yours may already be one of them — and two are free to read in full.

See the reports →
Specifications
VRAM
2 GB
Bandwidth
179 GB/s
FP16 Compute
2.5 TFLOPS
TDP
110W
Memory
GDDR5
Architecture
GCN 1.0
Stream Processors
1,280
Compute Units
20
PCIe
Gen 3 x16
48
Fast models · >30 tok/s
Real-time chat speed
48
Usable · >10 tok/s
Comfortable for all tasks
48
Total compatible
Fit in VRAM at Q4
Don’t want to buy?

Test Radeon R9 370 (or anything bigger) without committing. Pay by the second, cancel anytime.

Spin up in ~60s. Pay by the second. Cancel anytime.

Some links are affiliate links — we may earn a small commission at no extra cost to you. This helps keep FitMyLLM free and independent.

Compatible models· 48
S
Falcon-H1R Tiny 90M0.09B
Falcon·256K ctx· chat· reasoning
1768
tok/s · 27% VRAM
›
S
SmolLM2 135M0.135B
Smollm·2K ctx· chat
1179
tok/s · 29% VRAM
›
S
nomic-embed-text-v1.5 100M0.14B
Embedding·8K ctx· chat
1137
tok/s · 29% VRAM
›
S
GPT-2 124M0.14B
Gpt2·1K ctx· chat
1137
tok/s · 29% VRAM
›
S
SmolVLM 256M0.256B
Smollm·8K ctx· chat· vision
622
tok/s · 32% VRAM
›
S
Gemma 3 270M0.27B
Gemma·32K ctx· chat
589
tok/s · 33% VRAM
›
S
Snowflake Arctic Embed M v2.00.305B
Embedding·8K ctx· embedding· multilingual
522
tok/s · 34% VRAM
›
S
bge-large-en-v1.5 335M0.335B
Embedding·1K ctx· chat
475
tok/s · 35% VRAM
›
S
mxbai-embed-large-v10.335B
Embedding·1K ctx· embedding
475
tok/s · 35% VRAM
›
S
Snowflake Arctic Embed L0.335B
Embedding·1K ctx· embedding
475
tok/s · 35% VRAM
›
S
LFM2 350M0.35B
Lfm·125K ctx· chat· tool_use
455
tok/s · 35% VRAM
›
S
SmolLM2 360M0.36B
Smollm·8K ctx· chat
442
tok/s · 35% VRAM
›
S
GPT-2 Medium 345M0.38B
Gpt2·1K ctx· chat
419
tok/s · 36% VRAM
›
S
Qwen 2.5 0.5B0.5B
Qwen·32K ctx· chat
318
tok/s · 40% VRAM
›
S
SmolVLM 500M0.5B
Smollm·8K ctx· chat· vision
318
tok/s · 40% VRAM
›
S
Falcon-H1 0.5B0.52B
Falcon·128K ctx· chat
306
tok/s · 40% VRAM
›
S
BGE-M30.568B
Embedding·8K ctx· embedding
280
tok/s · 42% VRAM
›
S
Snowflake Arctic Embed L v2.00.568B
Embedding·8K ctx· embedding· multilingual
280
tok/s · 42% VRAM
›
S
Qwen3-Embedding 0.6B0.6B
Embedding·32K ctx· embedding· multilingual
265
tok/s · 43% VRAM
›
S
Falcon-H1R Tiny 0.6B0.6B
Falcon·32K ctx· chat· reasoning
265
tok/s · 43% VRAM
›
S
Falcon Perception 0.6B0.6B
Falcon·4K ctx· vision
265
tok/s · 43% VRAM
›
S
Qwen 1.5 0.5B0.62B
Qwen·32K ctx· chat
257
tok/s · 43% VRAM
›
S
LFM2 700M0.74B
Lfm·125K ctx· chat· tool_use
215
tok/s · 47% VRAM
›
S
Qwen3 0.6B0.75B
Qwen·32K ctx· chat· reasoning
212
tok/s · 47% VRAM
›
S
GPT-2 Large 774M0.81B
Gpt2·1K ctx· chat
196
tok/s · 49% VRAM
›
S
Qwen 3.5 0.8B0.87B
Qwen·256K ctx· chat· coding· multilingual
183
tok/s · 51% VRAM
›
S
InternVL3 1B0.94B
Other·32K ctx· chat· vision
169
tok/s · 53% VRAM
›
S
MiniCPM5 1B1.08B
Minicpm·128K ctx· chat· reasoning· multilingual
147
tok/s · 57% VRAM
›
S
K2 Horizon 0.9B1.08B
Other·128K ctx· chat· coding· reasoning
147
tok/s · 57% VRAM
›
S
TinyLlama 1.1B1.1B
Llama·2K ctx· chat
145
tok/s · 58% VRAM
›
S
LFM2.5-1.2B-Thinking1.2B
Lfm·122K ctx· chat· reasoning· tool_use
133
tok/s · 61% VRAM
›
S
Llama-3.2-1B1.2B
Llama·4K ctx· chat
133
tok/s · 61% VRAM
›
S
LFM2 1.2B1.2B
Lfm·125K ctx· chat· tool_use· multilingual
133
tok/s · 61% VRAM
›
S
Zamba2 1.2B1.2B
Other·4K ctx· chat
133
tok/s · 61% VRAM
›
S
EXAONE-4.0-1.2B1.3B
Exaone·64K ctx· chat
122
tok/s · 64% VRAM
›
S
OPT 1.3B1.3B
Opt·2K ctx· chat
122
tok/s · 64% VRAM
›
S
MiniCPM-V 4.61.3B
Other·256K ctx· chat· vision
122
tok/s · 64% VRAM
›
S
DeepSeek Coder 1.3B1.35B
Deepseek·16K ctx· coding
118
tok/s · 66% VRAM
›
S
Phi-1 1.3B1.42B
Phi·2K ctx· coding
112
tok/s · 68% VRAM
›
S
Phi-1.5 1.3B1.42B
Phi·2K ctx· chat· coding
112
tok/s · 68% VRAM
›
Next step

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Radeon R9 370.

What this card is worth

Radeon R9 370 holds 48 of the models in our catalogue and is, in practice, a Q4_K_M card — the largest it takes is LFM3-VL 2B at Q4_K_M.

Tokens/sec per $100
—
8B at Q4_K_M, so cards compare like for like
VRAM per $100
—
what memory costs on this card
The biggest it takes
LFM3-VL 2B1.92B · Q4_K_M1.7 GB54 tok/sest
Moondream2 1.9B1.9B · Q4_K_M1.7 GB54 tok/sest
LFM3 1.7B1.73B · Q6_K1.8 GB47 tok/sest
Falcon3-1B1.67B · Q5_K_M1.8 GB53 tok/sest
LFM2-VL 1.6B1.6B · Q5_K_M1.6 GB55 tok/sest
Falcon-H1 1.5B1.55B · Q6_K1.7 GB51 tok/sest
MiniCPM-V 4.7 1B1.55B · Q5_K_M1.6 GB56 tok/sest
Qwen2.5-Coder-1.5B1.5B · Q6_K1.6 GB52 tok/sest
Against cards of similar memory
M2 (8GB)5 GB$5992.8 tok/s per $100
M3 (8GB)5 GB$5992.8 tok/s per $100
M1 (8GB)5 GB$4992.2 tok/s per $100
RTX 2060 6GB6 GB$15026.7 tok/s per $100
Radeon R9 3702 GB——

Neighbours in memory rather than in price: memory decides whether a card can do the job at all, so two cards of the same size at different prices is the comparison you are making. Ordered by memory, then bandwidth — not by the value column, which is worked out from bandwidth and price alone and therefore rewards a cheap card whatever its software stack does to that bandwidth in practice. Read it as one input, not as a ranking.

Device under test

AMD Radeon R9 370 — 2 GB VRAM.

Radeon R9 370 spec
Brand
AMD
VRAM
2 GB GDDR5
Bandwidth
179 GB/s
FP16 Compute
2.5 TFLOPS
FP32 Compute
2.5 TFLOPS
Stream Processors
1,280
TDP
110 W
Architecture
GCN 1.0
AI capability
48/ 498 models @ Q4

With 2 GB VRAM and 179 GB/s bandwidth, this GPU handles models up to 1.61B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~20 tok/s.

Top models for Radeon R9 370
48 fit · showing 20
ModelSizeVRAM Q4tok/sAvg
GPT-2 XL 1.5B1.61B1.5 GB995.1
stablelm-2-1_6b1.6B1.5 GB999.5
Falcon-H1 1.5B1.55B1.4 GB10343.8
Qwen2.5-Coder-1.5B1.5B1.4 GB10619.6
Qwen2 Math 1.5B1.5B1.4 GB10619.6
Qwen 2.5 1.5B1.5B1.4 GB10630.2
Yi Coder 1.5B1.5B1.4 GB10614.6
Stella en 1.5B v51.5B1.4 GB10652.4
Phi-1 1.3B1.42B1.4 GB1127.2
Phi-1.5 1.3B1.42B1.4 GB1127.2
DeepSeek Coder 1.3B1.35B1.3 GB11816.8
EXAONE-4.0-1.2B1.3B1.3 GB12222.6
OPT 1.3B1.3B1.3 GB1225.3
MiniCPM-V 4.61.3B1.3 GB12228.5
LFM2.5-1.2B-Thinking1.2B1.2 GB13322.3
Llama-3.2-1B1.2B1.2 GB13310.1
LFM2 1.2B1.2B1.2 GB13315.6
Zamba2 1.2B1.2B1.2 GB13341.5
TinyLlama 1.1B1.1B1.2 GB14513.6
MiniCPM5 1B1.08B1.1 GB14730.8